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

Annotations only cover the safety profile (readOnlyHint=false, openWorldHint=true, destructiveHint=false), so the description carries the rest and does it well: it discloses the complimentary vs. connected-account song-count default, the roughly one-minute latency, the polling contract with poll_again, and the absence of an in-chat widget. These are behaviors an agent could not infer from the schema.

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?

Built from short, imperative sentences that front-load the action, then the follow-up polling flow, then the failure guard. It is slightly repetitive on end_user_id consistency, which is stated in the description and again in the schema, but no sentence is wasted.

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 7-parameter generation tool with no output schema and no nested objects, the description supplies everything an agent needs: what returns (generation_id to poll), how long it takes, how to detect completion, and what to do with the result. Nothing material is left to inference.

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 adds cross-parameter semantics beyond the schema: reusing the same end_user_id across every generate/status/library/take-down call, preferring artist_name over ai_cowriter_id, and the rule that the account tier (not the request) determines whether one or two songs come back. Some of this restates schema text, keeping it off 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?

Opens with a specific verb+resource pair ('Start a SoundBreak song generation with an AI artist'), naming the product and the actor. It is immediately distinguishable from siblings like get_song_generation_status, list_my_songs, or remove_song_preview.

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 routes to the alternative: poll get_song_generation_status with generation_id and the same end_user_id until generation_status is complete, keeping at it while poll_again is true. It also gives a pre-condition (do not invent end_user_id if missing) and a post-action (share listen_url, no in-chat widget).

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