get_document_pdf

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

With no annotations, the description carries the full burden and does well: it discloses the exact response payload keys and warns that unsupported types fail with a 404 rather than an empty result, which prevents a wasted retry loop. It does not cover auth/permission requirements or payload size limits for large PDFs, keeping it below a 5.

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 purpose and return shape, then constraints. Every sentence carries real information, though the full docType enumeration partially duplicates the schema enum and could have been compressed if brevity were paramount.

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 two-parameter read tool with no output schema, the description supplies what the schema cannot: the decoded response structure and the known failure mode for unsupported document types. An agent has everything needed to call it correctly and interpret the result.

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 enum and documentId are already documented structurally. The description restates the docType values and adds the useful caveat that purchase is excluded, but adds no new meaning for documentId — the baseline 3 applies.

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 ('Get the PDF of a document') plus the encoding format and API version. The named return shape ({ contentType, base64, bytes, filename }) makes it unmistakable from get_document, which returns document data rather than a binary artifact.

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?

The description gives an explicit supported docType list and an explicit exclusion: 'purchase is NOT supported — GET /purchases/{id}/pdf returns 404', plus a note that purchaserefund has no v2 CRUD support. That is clear when/when-not guidance; what's missing is a pointer to a fallback tool for purchases, so it stops short of the top score.

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