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

With annotations already covering the safety profile (readOnly/openWorld/non-destructive), the description still adds substantial behavioral context: 10 MB input limit, text outputs returned as content vs. binary outputs as file_base64, the explicit limitation that local includes and remote images are not loaded, and per-call pricing ($0.01 USDC via x402 on four chains).

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?

Front-loaded with the core purpose and formats, then the input/output mechanics and constraints. The pricing sentence and inline sample add length but are genuinely useful; the run-on paragraph could be broken up but there is little pure filler.

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?

For a stateless conversion tool with no output schema, the description covers inputs, output encoding, detection behavior, limitations and billing — everything an agent needs to invoke it correctly and predict the response shape.

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 mapping each input channel (content text, file_base64 binary, url), restating 'to' as required, and clarifying auto-detection of 'from'. It also adds the 10 MB size cap for file_base64 that the schema does not state, though it does not explain the 'title' parameter.

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 ('Convert documents between formats') and the exact resource, enumerating the supported formats (Markdown, HTML, DOCX, ODT, EPUB, RST, LaTeX, RTF, plain, PDF). This specificity makes it clearly distinguishable from siblings like doc_parse, pdf_extract and html_to_pdf.

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?

It explains the three input modes (content / file_base64 / url), that 'from' is auto-detected when omitted, and includes a concrete sample call. However, it never states when to pick doc_convert over close alternatives such as doc_parse, pdf_extract or html_to_pdf, so usage is only implied.

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