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

With no annotations, the description carries the burden and does real work: it discloses the async job model, the output shape (vertical 9:16, captioned, sentence-boundary cuts, 15-60 s), and that a style is optional. It does not mention the rights_attested gate, expected job duration, or failure behavior for unsupported sources, which are the remaining behavioral gaps for a long-running generation tool.

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?

Dense but front-loaded: the core operation leads, the ranking signals follow, and the job_id/poll instruction closes it. Every clause carries information, though the long signal enumeration in parentheses pushes the sentence toward list-dump territory and could be trimmed without loss.

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 no-output-schema, async generation tool this is close to self-sufficient: the agent knows the input is a link, the result is a job_id, and the next call is clips_status. The only meaningful omission is that the first-time rights attestation requirement lives solely in the schema and is not surfaced as a usage precondition.

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 60%, so the description only needs partial compensation. It adds meaning for `style` by framing it as an 'optional originality style' and implicitly ties clip length/captioning to outcomes, but says nothing about `top_n`, `platform`, or `rights_attested` beyond what the schema already encodes. Adequate at baseline, not additive.

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 ('Paste-a-link clipping (clips.generate)') and then enumerates exactly what it produces: 15-60 s 9:16 captioned clips cut on sentence boundaries from ranked moments. The parenthetical API name plus the signal list (most-replayed, timestamped comments, live-chat spikes, audio, motion) makes it unmistakable and clearly distinct from clips_status, which is the polling counterpart.

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 a clear entry condition (paste a link) and an explicit follow-up path: 'Returns a job_id; poll clips_status.' That routes the agent through the async workflow rather than implying the clips come back inline. It stops short of stating when NOT to use it (e.g. for local files without rights, or when a script is wanted instead of clips), so it is strong but not fully exclusionary.

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