convert_to_csv

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (which only declare idempotency/safety), the description details critical behavioral specifics: dual return modes (string vs JSON object), file system side effects (creates parent directories, overwrites existing files), and content handling (multiple tables concatenated with blank lines, non-table content ignored, no-tables returns empty string).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Six sentences covering distinct aspects: conversion logic, content handling, side effects, return values, and usage recommendations. Every sentence provides unique information not redundant with the schema or annotations. Slightly dense but appropriate for the complexity of dual-output behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without an output schema, the description fully compensates by detailing return structures (CSV string vs JSON object with specific fields), edge case behaviors (empty input handling), and side effect warnings necessary for safe invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, baseline is 3. The description adds value by connecting output_path to behavioral outcomes (overwriting existing files) and explaining the conditional return type logic tied to this parameter, though it doesn't significantly expand on the markdown parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb-resource combination ('Extract tables from Markdown and convert them to CSV format') and explicitly distinguishes from siblings by naming 'convert_to_xlsx' and 'convert_to_json' as alternatives for different use cases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('lightweight tabular export or when downstream tools expect CSV') and provides clear alternatives ('Prefer convert_to_xlsx for Excel-compatible spreadsheets... or convert_to_json for structured data'), guiding the agent away from incorrect selections.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.