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

Annotations only supply the generic non-read-only/non-idempotent profile; the description adds the async analysis pipeline, expected latency (~1 minute), the lyrics-mismatch refusal behavior after analysis, and the fact that cover art is re-encoded at 1536/640/160 px rather than stored as uploaded. It also discloses the plan/storage gating that no annotation conveys.

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?

Front-loads the action and required inputs, then layers constraints, async behavior, and errors in a logical order. It is dense with specifics rather than filler, though the single long paragraph could be broken up for faster scanning.

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 compensates fully: it tells the agent what to poll (get_song, analysis.status), what a successful completion looks like ("ready"), what warnings to expect (lyrics mismatch), and which account fields gate the call. Nothing needed to invoke or verify the call is missing.

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; the description still adds real value by giving accepted formats and size limits for the audio and cover URL parameters (MP3/WAV/M4A ≤250 MB; square JPEG/PNG 1000–6000 px ≤20 MB) and by explaining that artist_id may be omitted in an artist workspace. The lyrics caveat about repetition and partial coverage further clarifies semantics beyond the schema text.

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?

"Add a song: master audio and square cover art" names the verb, resource, and the two required inputs, which cleanly separates it from siblings like create_artist, add_artist_photos, and create_lyric_video. An agent can identify what this creates without opening the 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?

It states preconditions (active plan, storage room), the follow-up sequence (poll get_song until analysis.status is "ready"), and an explicit alternative path for later edits (set_song_lyrics). It also names the failure modes (402 plan_required, 402 storage_full) with the sibling to check.

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