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

Annotations flag destructive/openWorld/non-idempotent, but the description adds substantive behavior: it spends the owner's credits, filming takes minutes so poll rather than assume failure, it cannot be cancelled through this flow, and outcome_unknown does not mean failure (do not retry, reconcile first). This is exactly the value-add the annotations cannot convey.

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 and front-loaded, opening with the action and immediately followed by the credit-spend warning. It is long, but nearly every sentence carries operational information; minor load comes from stacking cancellation, polling and recovery caveats in one block.

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 destructive, credit-spending, open-world call with no output schema, it covers the return shape (generation id and phase), the polling path, the failure path, and the caveat that the flow has no cancel. An agent has everything needed to call it and react to results.

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 100%, so the baseline is 3, but the description adds real semantics: pass all four ids EXACTLY as soclo_quote returned them, expectedCredits is a hard ceiling (Soclo refuses to charge more than the quote), and the ancestor SQL semantics of reusing the same clientRequestId when repeating an identical call.

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: 'Film a quoted storyboard into a finished video advert.' This distinguishes it cleanly from nearby siblings (soclo_video_prepare, soclo_video_variants_approve, soclo_video_poll) by naming it as the actual filming/rendering action.

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 explicit when-to-use (confirm owner approved the soclo_quote price first), the required upstream dependency (projectId/revision/quoteId/expectedCredits from soclo_quote), and the alternatives for follow-up (soclo_video_poll, soclo_video_status) and recovery (soclo_video_recover). Nothing is left to inference.

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