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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false), so the description is free to add what they cannot: the two-URL return contract, the HTTP PUT requirement, and the fact that a browser upload auto-starts transcription. It does not address whether calling twice creates duplicate uploads (relevant given idempotentHint=false) or any auth requirements.

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 sentences, zero filler: the eligibility condition comes first, then the return contract with the action required for each URL. The parenthetical example ('a file attached in another chat app') is doing real disambiguation work.

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 10 parameters, no output schema, and full schema coverage, the description fills exactly the gap that matters: what the call returns and what to do with each return value. Nothing an agent needs in order to invoke 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 filename, content_type, size_bytes, model, and the boolean extras are already well documented in the schema. The description adds no parameter-level meaning — upload_url and upload_page_url are return values, not inputs — so 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?

The description clearly scopes the tool to files that are neither public links nor ChatGPT attachments, which is a meaningful resource distinction. It never names the sibling tools (transcribe_url, transcribe_file) that handle the excluded cases, so the agent must infer the routing from the negative condition rather than being told outright.

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 when-not condition is explicit (not a public link, not a file attached in a ChatGPT chat) and the follow-up workflow is spelled out: PUT the file to upload_url then call start_transcription, naming that sibling directly. The alternative path (upload_page_url for a browser upload) is also given. The only gap is that the tools to use for the excluded cases are never named.

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