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

With no annotations, the description carries the full behavioral burden. It does disclose the return semantics (ranked clips with a 0-100 virality score, per-signal breakdown, reasons) and that results only appear when the job is done, which is real added context. It omits failure/expiry states, whether the job record is retained, and any read-cost or rate-limit characteristics.

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?

A single dense sentence, front-loaded with the operation and followed by the payoff payload. Every clause carries information; nothing is padding.

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?

There is no output schema, so the description must describe return values, and it does so with the score range and breakdown fields. For a one-parameter polling tool that is close to sufficient; only job-state edge cases (pending, failed, expired) are left uncovered.

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 0% and the single job_id parameter is documented nowhere else, but the description implies its provenance by calling it 'a clips_generate job', telling the agent the id comes from that sibling's output. It adds no format, validation, or reuse/expiry detail beyond that implication.

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 resource and operation: polling the status of a clips_generate job, and names the sibling that produces the job_id, so the async relationship is unambiguous. It also previews the payload (ranked clips, virality score 0-100, per-signal breakdown, reasons). It stops just short of a crisp verb phrase like 'Poll', but an agent can still route correctly.

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?

'when done' implies this is polled after clips_generate completes, which is implicit when-to-use guidance. There is no explicit instruction such as 'call repeatedly until status is complete', no polling interval, and no statement about what to do if the job fails or the id is unknown.

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