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

Beyond the annotations it discloses two behaviors the agent could not otherwise know: the job is asynchronous, and output length is generator-controlled and cannot be requested or limited, making regeneration an ineffective length fix. It also discloses credit cost and forbids silent variants. It stops short of clarifying why destructiveHint=true is set (e.g. whether an existing asset could be overwritten) or what the immediate response contains before the job completes.

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?

Purpose and mode guidance are front-loaded, and the exclusions and follow-up tools come before the spend caveat, which is the right ordering. The external spend paragraph is long but each clause constrains a distinct failure mode (extra variants, longer durations, higher quality, extra outputs), so little 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, credit-spending async generation tool with no output schema, the description covers the workflow (job submission, then track_progress, then edit_item), the length constraint, and the cost gate. Gaps remain around what name does, what timelineId implies, and what identifiers come back on submission, but nothing critical to calling it correctly 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 71%, and the description still adds real meaning: prompt is required for instrumental but optional for song, lyrics belongs to song mode, and gender is a song-mode preference. It does not add anything for name or timelineId, which remain semantically thin in both places.

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 ('Submit an instrumental or vocal music generation job and create an audio asset in the project library') and immediately narrows scope with the instrumental/song mode split, which separates it from siblings like submit_sound, submit_voice, and submit_video. An agent can tell what this tool produces 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?

Gives explicit selection criteria ('generationType=instrumental for BGM/music beds (mureka-9), or generationType=song for an original sung song with lyrics (mureka-9.5)'), explicit exclusions ('does not place or replace timeline items'), the follow-up path (track_progress then edit_item), and a hard precondition for calling at all (spend rule: only when the request clearly covers this exact generation).

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