wait_for_song

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

With no annotations, the description carries the full burden and excels. It discloses polling limits (~45 seconds), return behavior on success vs. still rendering, idempotency (safe to call repeatedly), and that it never starts a new song. This is rich behavioral context.

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?

Three sentences, front-loaded with the main purpose, then behavioral details, then safety. Every sentence earns its place with no redundancy or fluff.

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?

Despite no output schema, the description fully explains the polling loop, success/retry paths, and safety profile. It is complete for a two-parameter tool with no annotations, covering both how and when to use it.

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 baseline is 3. The description adds meaning by referencing 'same job_id' for retries and the ~45-second polling window, which complements the schema's max_wait_seconds parameter and clarifies intended usage.

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?

The description uses a specific verb+resource ('Wait for a song job to finish and return the audio') and clearly distinguishes itself from siblings: it polls for completion rather than just checking status (check_song) or creating a job (generate_song).

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?

It gives clear context: use it after generating a song, and if not ready, call again with the same job_id. It implicitly differentiates from alternatives by stating it returns audio when ready, but does not explicitly mention check_song as an alternative for status-only checks.

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