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

Annotations already establish readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real behavioral context beyond them: a hard 25 MB input cap, the accepted output format (Markdown), the two mutually exclusive input modes, and an explicit per-call cost of $0.01 USDC via x402 — the last being important for agent budgeting and rarely surfaced elsewhere.

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?

Two tight sentences, front-loaded with the core verb and supported formats, followed by the input contract and cost. The format enumeration is information-dense rather than padding, and no sentence restates the title or wastes tokens.

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?

With readOnly/openWorld annotations present and no output schema, the description carries only part of the burden, and it does so well: it states the output format, input modes, size cap, and cost. It stops short of noting failure modes (bad URL, unsupported format, page limits) or routing to sibling converters, which keeps it just under complete.

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 description coverage is 100% and each of the three parameters is documented in-schema, so the baseline is 3. The description reinforces the url-vs-base64 alternation and the filename pairing rule and adds the 25 MB limit, but it introduces no syntax, format, or edge-case detail the schema does not already carry.

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?

Strong specific verb+resource: converts an enumerated set of document formats (PDF, docx, xlsx, ODS/ODT, CSV, HTML, XML, images) into clean Markdown. An agent immediately knows what the tool produces. However, it never distinguishes itself from close siblings in the same namespace (doc_convert, office_convert, convert, pdf_tools, ocr), so it falls short of a 5.

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 gives concrete invocation mechanics — 'Send a public file URL or base64 file plus filename (max 25 MB)' — which is genuinely useful. But it offers no when-to-use/when-not guidance and never names an alternative sibling (doc_convert, office_convert, ocr), so selection between similar tools is left entirely to inference.

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