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

No annotations, so the description carries the full burden and does so richly: asynchronous processing, AI-searchable once ready, multimodal vision for images, a gateway-level 32 MB request-body cap that fails with an HTML (not JSON) error, and base64 ~33% inflation. This is exactly the behavioral context a caller needs.

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-loads async behavior and the sibling distinction before formats and transport limits, and every sentence carries information. It is dense and long, but the length is justified by the number of real constraints it must convey.

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 5-param, no-output-schema upload tool, it covers async semantics, polling, size/transport limits, and the return_html tradeoff is handled by the schema. Only minor gaps remain, such as the session_id ambiguity and lack of explicit error-handling guidance beyond the gateway cap.

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 80%, so the baseline is 3; the description adds the 50 MB validation limit, the base64 encoding context, and the filename-driven type detection. Slight tension: it states 'Requires session_id' while the schema says session_id is auto-generated if not provided.

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+resource (upload attachment) and explicitly differentiates from the sibling upload_document_base64, explaining attachments are read-only AI context rather than the editable working document. An agent can pick it correctly without opening either 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?

Gives clear conditions: poll get_attachment_status for readiness, and use request_upload_url beyond ~20 MB of file bytes. It names the alternative and its trigger. Lacks an explicit 'when not to use attachments at all', so a 4 rather than 5.

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