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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the bar is lower, yet the description adds genuinely useful context beyond them: that the call spends credits, that it returns video ids immediately (asynchronous), that each video yields one file per requested format, and that polling is required. Minor gap: it does not say what happens to already-spent credits on a failed render.

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?

Four compact sentences, cost and the quote linkage front-loaded, each sentence carrying distinct information (pricing, request contract, return shape, format layout). The garbled first clause costs a point but nothing is padded.

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 9-parameter, nested-object mutation with no output schema and a sibling polling tool, the description covers the essentials an agent needs: credit spend, quote matching, immediate id return, polling target, and per-format file output. It could be stronger on failure/refund behavior and on how variations map to returned ids, but the core call path is complete.

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 all nine parameters are already documented in the schema, including quote_id's 'request must be identical' note and the same-value constraints on metadata and callback_url. The description restates the identical-request requirement, adding only marginal semantics beyond the schema, so the baseline of 3 applies.

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+resource ('Make the lyric video') and frames it as the paid execution step of a previously obtained quote, which distinguishes it from quote_lyric_video without naming it directly. An agent can infer it is the render step, but the awkward phrasing ('Make the lyric video a quote priced') and the absence of an explicit sibling reference keep it from a 5.

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 clear sequencing: send the same request as the quote plus its quote_id, then poll get_video until completed or failed. It names the follow-up tool explicitly. However, it never states the prerequisite that quote_lyric_video must have been called first, nor when this tool is inapplicable, so it stops short of full when/when-not guidance.

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