Poll / download music

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

Annotations only signal that this is not a pure read (readOnlyHint=false) and is otherwise safe; the description supplies the materially important behavior: the file is written to disk and can be retrieved only once on /v1, so a missed retrieval is unrecoverable, and the call is free. That one-time-retrieval warning is exactly the kind of context annotations cannot express, though the tension with idempotentHint=true for the download path is left unexplained.

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?

A single dense sentence with no filler, front-loaded with the action and ending with the cost note. Every clause (source tool, disk save, one-time retrieval, free) carries decision-relevant information.

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 two-parameter tool with no output schema, the description covers what triggers it, what it returns, the one-shot retrieval constraint, and pricing. It leaves out failure/timeout behavior and what a call returns before completion, but the wait_seconds schema note partially fills that gap.

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 50%: wait_seconds is fully documented in the schema, but job_id has no schema description. The description partially compensates by telling the agent job_id comes from carpe_music_generate, but adds nothing about format, reuse, or post-completion behavior of that id.

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 ("Check a music job") and explicitly ties the job to its producer, carpe_music_generate, which distinguishes it from the image/video status siblings without opening any schema. It also states the outcome at completion (track saved to disk and returned).

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 usage context is unambiguous: call this after carpe_music_generate, and the wait_seconds schema note tells the agent to poll later with the status tool for longer jobs. It doesn't state an explicit when-not or name a fallback sibling for job tracking, so it stops short of full routing guidance.

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