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

Annotations declare the safety profile (readOnly=false, destructive=false, openWorld=true, idempotent=false), so the description needn't restate it. It adds genuinely non-structured context by flagging that this is an asynchronous job 'like flowmusic_create_song', implying the agent must poll for completion, plus the default extend window.

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 short fragments, front-loaded with the purpose before the default and the job note. The trailing 'POST /music/edit operation extend' is an internal routing detail of marginal use to an agent, but overall it is tight and wastes little.

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 100% schema coverage and annotations present, the definition is workable, and noting the job semantics helps. However it omits how the result is retrieved (flowmusic_get_job), what happens to the source clip, and any prerequisite that the clip must come from a finished job, leaving gaps for a mutating job-launching tool.

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 description coverage is 100%, so every parameter including clip, seed, model, title, extend_s, and extend_from_s is already documented in the schema. The description's '(default 150 s from its end)' merely echoes the schema defaults and adds no new syntax or format detail beyond it.

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 gives a specific verb and resource: 'Add music to a clip, as described in instruction', which is the extend operation. It distinguishes the async-job nature by referencing create_song, but does not differentiate itself from close siblings like flowmusic_replace_section or flowmusic_cover_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 states the default behavior (150 s from the end) and that it is a job, but gives no guidance on when to choose extend over create_song, replace_section, or cover_song, nor any prerequisites such as requiring a finished-job clip. Usage is only implied at best.

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