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

Beyond readOnlyHint=true, it discloses cost ('Free'), latency ('Waits up to 20 s'), and a critical non-obvious behavior: no `history` is returned, so the caller must append its message and this reply before the next director call. It also warns that captions are always whole-line, never word-synced. These are exactly the traits that affect correct invocation.

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-loaded with the most decisive facts (free, blocking, no history), then Args and Returns blocks. The caption-sync note is somewhat tangential to fetching a turn but is short and relevant to the returned plan, so little waste overall.

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?

No output schema exists, so the explicit Returns listing (ok, turn_id, status, reply, music_plan, chips, dropped, plus the poll_again branch) is essential and present. Minor gap: fields like `dropped` and `chips` are not explained, and no `next_tool` value is named.

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 0%, so the description has to carry the parameter meaning, and it does specify that turn_id comes from music_video_director. It does not restate the mt_<hex>_<hex> pattern, but the schema's pattern already enforces that.

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 states a specific behavior: it fetches the answer of a music_video_director turn that was still running, making clear this is a result-retrieval/polling tool rather than a turn creator. It is distinguishable from music_video_director, though the leading verb is implied ('The answer of...') rather than stated as 'get/poll'.

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 tells the agent when this applies (a director turn that was still running) and what to do if the turn is still pending ({poll_again, next_tool}), which is concrete routing guidance. It does not name an explicit alternative tool or a when-not-to-use case, so it stops short of a 5.

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