Tool Description Review:
- [ ] Prerequisites stated (packages, API keys, accounts)
- [ ] Critical abbreviations expanded on first use
- [ ] Required vs optional parameters clear
- [ ] Mutually exclusive options numbered/labeled
- [ ] Parameter guidance includes trade-offs
- [ ] Filter syntax shows available fields
- [ ] File size warnings where relevant
- [ ] Examples show realistic usage

// Before
"description": "Process BED regions, motifs, or gene lists..."

// After
"description": "Process genomic data. **Required: Provide ONE input type** - (1) BED regions, (2) DNA motif, or (3) gene list. Analyzes..."

"description": "Query single-cell data. Prerequisites: Requires 'package-name' (install: pip install tooluniverse[extra]). Returns..."

// Before
"description": "Download H5AD files..."

// After  
"description": "Download H5AD (HDF5-based AnnData) files..."

"parameter_name": {
  "type": "string",
  "description": "Filter using SQL-like syntax. Format: 'field == \"value\"'. Operators: ==, !=, in, <, >, <=, >=. Combine with 'and'/'or'. Common fields: tissue, cell_type, disease, assay, sex, ethnicity. Examples: 'tissue == \"lung\"', 'disease == \"COVID-19\" and tissue == \"lung\"', 'cell_type in [\"T cell\", \"B cell\"]'."
}

// Before
"threshold": "Q-value threshold (05=1e-5, 10=1e-10, 20=1e-20)"

// After
"threshold": "Peak calling stringency. '05'=1e-5 (permissive, more peaks, broad features), '10'=1e-10 (moderate, balanced), '20'=1e-20 (strict, high confidence, narrow peaks). Default '05' suitable for most analyses. Higher values = fewer but more confident peaks."

"bed_data": {
  "description": "**Option 1**: BED format regions (tab-separated: chr, start, end). Example: 'chr1\\t1000\\t2000'."
},
"motif": {
  "description": "**Option 2**: DNA sequence motif in IUPAC notation. Use: A/T/G/C, W=A|T, S=G|C. Example: 'CANNTG'."
},
"gene_list": {
  "description": "**Option 3**: Gene symbols as array. Example: ['TP53', 'MDM2']."
}

"description": "Download contact matrices. Note: Files can be large (GBs), check file_size in metadata before downloading. Returns..."

"description": "Perform enrichment analysis. Note: Returns submission URL (web form-based analysis). Analyzes..."

"file_type": "File format. Common types: 'cooler' (multi-resolution contact matrices), 'pairs' (aligned read pairs), 'hic' (Juicer format), 'mcool' (multi-resolution cooler)."

{
  "name": "Tool_operation_name",
  "type": "ToolClassName",
  "description": "[Action verb] to [purpose]. [Prerequisites if first tool]. [Key data/features]. [Required inputs if mutually exclusive]. [Note about limitations/requirements]. Use for: [use case 1], [use case 2], [use case 3].",
  "parameter": {
    "properties": {
      "param_name": {
        "type": "string",
        "description": "[What it does]. [Format/syntax if applicable]. [Options with trade-offs]. [Examples]. [Recommendation if applicable]."
      }
    }
  }
}

"description": "Query [data type] from [source]. [Prerequisites]. Filter by [criteria]. Returns [output]. [Data scale]. Use for: [discovery], [analysis], [specific research tasks]."

"description": "Download [file types] from [source]. [Format details]. [File size warning]. [Authentication requirement]. Use for: [offline analysis], [custom processing], [integration]."

"description": "Analyze [input type] to find [results]. **Required: Provide ONE input type** - (1) [option], (2) [option], (3) [option]. Compares against [database/background]. [Result format]. Use for: [identifying], [discovering], [predicting]."

# Validate all tool JSONs
python3 -m json.tool src/tooluniverse/data/your_tools.json > /dev/null && echo "✓ Valid"

# Check all tools in category
for f in src/tooluniverse/data/*_tools.json; do
  python3 -m json.tool "$f" > /dev/null && echo "✓ $f valid" || echo "✗ $f invalid"
done

{
  "name": "Tool_enrichment",
  "description": "Perform enrichment with tool to find factors.",
  "parameter": {
    "properties": {
      "bed": {"description": "BED data"},
      "motif": {"description": "Motif"},
      "genes": {"description": "Genes"},
      "threshold": {"description": "Threshold value"}
    }
  }
}

{
  "name": "Tool_enrichment_analysis",
  "description": "Identify transcription factors enriched in your data. **Required: Provide ONE input type** - (1) BED genomic regions, (2) DNA sequence motif (IUPAC notation), or (3) gene symbol list. Compares against 400,000+ ChIP-seq experiments. Returns ranked proteins with enrichment scores. Note: Returns submission URL (web-based analysis). Use for: identifying regulators of regions, finding proteins bound to motifs, discovering transcription factors regulating genes.",
  "parameter": {
    "properties": {
      "bed_data": {
        "description": "**Option 1**: BED format regions (tab-separated: chr, start, end). For finding proteins bound to genomic regions. Example: 'chr1\\t1000\\t2000'."
      },
      "motif": {
        "description": "**Option 2**: DNA motif in IUPAC notation (A/T/G/C, W=A|T, S=G|C, M=A|C, K=G|T, R=A|G, Y=C|T). Example: 'CANNTG' (E-box)."
      },
      "gene_list": {
        "description": "**Option 3**: Gene symbols as array or single gene. Example: ['TP53', 'MDM2', 'CDKN1A']."
      },
      "threshold": {
        "description": "Peak stringency. '05'=1e-5 (permissive, more peaks), '10'=1e-10 (moderate), '20'=1e-20 (strict, high confidence). Default '05' suitable for most analyses."
      }
    }
  }
}