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

With no annotations, the description carries the full burden and does so well: it discloses the non-billable upload/parse model (charged only on AI edits), the compact-by-default response to protect context, that the document is loaded into the session and edited via chat, and that attachment mode processes asynchronously returning a job_id to poll. These are non-obvious, high-value behavioral facts an agent could not infer from the schema.

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?

Content is dense and front-loaded, leading with the verb and pipeline rather than burying it, and every sentence carries information. However, it is delivered as one long run-on paragraph with several em-dash asides, which hurts scannability for a definition this content-rich.

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?

An output schema exists so return values needn't be explained, and the description covers the workflow prerequisite (request_upload_url), both parse modes, the async job_id path, the default response shape, and the billing model. For a 6-parameter parsing/ingestion tool with no annotations, nothing essential to calling it 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 83%, so the schema already documents filename, upload_id, session_id, parse_mode, and return_html in detail, and the description largely restates the parse_mode and return_html semantics rather than adding new syntax or constraints. The added framing (edit-via-chat, context-size tradeoff) is useful but not parameter-level detail, so the baseline 3 holds.

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 ('fetches the file uploaded via request_upload_url and runs the same parsing pipeline as upload_document_base64') and immediately positions itself relative to two named siblings, making the distinction from upload_document_base64 explicit. The scope of what gets parsed (paragraphs, headings, tables, rows, cells) further sharpens what the tool actually produces.

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?

Clearly conditions usage on the preceding request_upload_url call and explains the parse_mode='document' vs 'attachment' choice and the return_html default. It does not explicitly state when to prefer this over upload_document_base64/upload_attachment_base64, leaving the routing between upload paths to inference.

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