doc_convert

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

With no annotations, the description carries the full burden and does so well: it discloses cost ($0.01 USDC/call), p99 latency (8000ms), a 10 MB size cap, the output representation (text as content, binary as file_base64), and a real limitation ('Local file includes and remote images are not loaded'). It stops short of describing auth/payment mechanics or failure modes, so it is strong but not exhaustive.

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?

Dense but front-loaded: purpose and format list come first, then input modes, output behavior, limitations, params, and cost/latency. Every clause carries information, though the trailing 'Params:' enumeration partially restates the schema rather than only adding to it.

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?

No output schema exists, and the description explains the return shape (content for text outputs, file_base64 for binary outputs), which is exactly the missing piece. Combined with cost, latency, size limits, and format coverage, an agent has what it needs to call this correctly.

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?

Schema coverage is 67%, and the description compensates by listing to (required), the mutually exclusive input options (content OR file_base64 OR url), from, and title, and by clarifying which formats file_base64 accepts (docx, odt, epub, rtf) plus the 10 MB limit. The mutually-exclusive input pattern is documented in prose only, which adds genuine value over the schema.

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?

States a specific verb and resource ('Convert documents between formats with pandoc') and enumerates the supported formats and input modes. An agent can tell this apart from extraction siblings like doc_parse or pdf_extract, which take a document and return one form rather than converting between arbitrary formats.

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?

Gives clear context on how to invoke it: choose text (content), binary file (file_base64), or url, and the input format is detected automatically or forced via from. It does not, however, name alternatives or state when NOT to use it (e.g. vs doc_parse or html_to_pdf), so routing guidance is implied rather than explicit.

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