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

Annotations already declare this is a non-read-only, non-idempotent, open-world call, and the description usefully adds the async job pattern and the job_id/robot_key return values. It says nothing about cost or credit requirements, which matters given the estimate_cost and pay_job siblings, nor about limits or duplicate-job behavior implied by idempotentHint=false.

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 waste: what it does and what to do next. The workflow pointer is front-loaded in the second clause.

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 no output schema, the description correctly discloses that the call returns job_id and robot_key and how to continue with get_job, which is the minimum an agent needs. The missing piece is the monetization/allocation context hinted at by the pay_job and estimate_cost siblings.

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 every parameter is already documented in the schema, including the model enum and the robot_key carry-over rule. The description only reinforces the robot_key lifecycle by noting it is returned; baseline 3 applies when the schema does the heavy lifting.

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 ("Start transcribing a media file") and qualifies the source as "a public link", which separates it from transcribe_file. It does not distinguish itself from the sibling start_transcription, so an agent comparing those two still has to infer the difference.

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?

"Returns job_id and robot_key; then poll get_job" gives explicit follow-up guidance and names the sibling to use next. It stops short of stating exclusions (e.g., when to prefer transcribe_file or start_transcription), but the link-vs-file condition is clearly implied.

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