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

Annotations only give the generic safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorld=true), but the description goes far beyond: output is a non-reflowable LibreOffice docx with one text box per line, tables/links/forms convert poorly, scanned PDFs need OCR first, encrypted input returns 422, density/page overflow returns 422, >15 MB output returns 413, ~78 s returns 503, typical latency 2-20 s, price USD 0.01 with no free tier, and returned text must be treated as untrusted. This is unusually rich disclosure.

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?

Reasonably front-loaded: purpose and sibling routing come first, then mechanics, limits, and pricing. Every sentence carries information (format caveats, status codes, timing, cost, injection warning), though the density is high and some readers would benefit from grouping. No filler, but it is long for a single tool.

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 an output schema present, return-shape detail is unnecessary, and the description still adds cross-cutting context (pricing, latency, failure codes, prompt-injection caution) plus the sibling routing needed among dozens of PDF tools. Nothing an agent needs to call this correctly is missing.

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%, so the baseline is 3; the description adds real meaning on top by explaining that 'output=url' yields a 24 h link that keeps the file out of the context window, and that 'pages' converts in parts when exceeding the 50-page cap. It stops short of documenting url/pdf_base64 mutual exclusivity, but the schema already covers size limits and the url/base64 alternatives.

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 precise verb+resource ('convert a PDF to Word (.docx)') and immediately distinguishes itself from siblings, naming convert_office_to_pdf for the reverse and convert_document_to_markdown for plain text. An agent can select or reject this tool without opening any schema.

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?

'Use when an agent must convert a PDF to Word (.docx) for editing' gives the trigger condition, and the two named alternatives cover the adjacent cases (reverse conversion, plain text). Explicit when-to-use plus explicit alternatives is the top of the scale.

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