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

Annotations already declare openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds important behavioral context: it returns job_id and robot_key, the job is asynchronous, and you must poll get_job. It doesn't mention rate limits or failure modes, but the core async contract is disclosed.

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?

Single sentence, front-loaded with the action and source constraints, then the return contract and next step. Zero waste and every clause earns its place.

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?

Given no output schema, the description discloses the return values (job_id, robot_key) and the follow-up poll. The schema fully covers parameters. The only gap is that it doesn't route away from the sibling start_transcription, but for an 8-param tool with 100% schema coverage, this is nearly complete.

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 schema documents all 8 parameters including the model enum, language auto-detect, and robot_key grouping semantics. The description adds no parameter detail beyond what the schema provides, 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?

States a specific verb (start transcribing), resource (media file from a public link), and accepted sources (direct file link or YouTube). It distinguishes itself from siblings like start_transcription and create_upload by specifying the input is a URL.

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?

Explicitly says to call it to start a job, then poll get_job, which is a clear workflow instruction. It does not contrast with start_transcription or create_upload, so it doesn't reach the 5 level of naming alternatives.

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