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

Annotations only supply idempotentHint=false; the description carries the rest and does so well, disclosing the 100 MB size cap, the 15-minute validity window, single-use semantics, and that the file is held in memory only until transcription or expiry. Those are exactly the behavioral traits an agent needs and cannot get from structured fields.

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 the purpose and constraints, then the two upload paths, then the required next call. Every sentence carries new information; the curl example is directly actionable rather than filler.

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 zero-parameter tool with no output schema, the description covers everything the agent needs: what it returns (a link plus an upload_id), how to use it, how long it lasts, and the dependency on transcribe_upload. Nothing material 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?

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline is high. The description appropriately focuses on the returned upload_url/upload_id values the agent must carry forward instead.

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 ('Create a one-time link to upload one audio file') plus the hard constraints (100 MB, 15 minutes). An agent can distinguish this from transcribe_upload/transcribe_url without opening any schema, and the one-time nature is called out up front.

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 explicit context for both invocation paths (shell via curl, or a human opening the link in a browser) and names the mandatory follow-up sibling, 'Then call transcribe_upload with the upload_id.' The when-to-use chain is fully specified rather than implied.

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