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

Annotations already cover read-only/idempotent/non-destructive, and the description adds a full status state machine beyond that: what each state returns (transcript formats, download links, zip_url, summary, action_items, translations; 100-word preview plus payment_url; error message) and the 24-hour deletion window. This is exactly the behavioral context annotations cannot express.

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?

Purpose and job_id provenance are front-loaded, then each status is quoted and paired with its payload in a compact clause. Roughly 110 words with no filler — every sentence conveys a state, a polling rule, or a return value.

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?

No output schema exists, so the description carries the full burden of describing returns — and it does so per status, including the ZIP aggregate, preview/payment path, and failure/deletion cases. An agent has everything needed to call it, poll it, and interpret each response.

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 100%, so the baseline is 3, but the description still adds provenance for job_id (including transcribe_file, which the schema omits) and ties the format parameter to its output consequence ("the transcript in the chosen format"). robot_key is left entirely to the schema, which keeps it from a 5.

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 ("Status and results of one job") and immediately scopes it to a known job_id. It also names the sibling tools that produce a job_id (transcribe_url, transcribe_file, create_upload) and the sibling that recovers a lost one (list_jobs), so it is distinguishable without opening any 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 explicit when-to-call guidance per state: poll every 10-20 seconds while waiting_for_upload/queued/processing, call again after the user pays on payment_required, and use list_jobs when the job_id is lost. The alternative tool and the condition selecting it are both named.

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