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

Annotations cover safety/idempotency hints, and the description adds substantial non-obvious behavior: credit costs and comp-credit usage, immediate start, a 60-second full-refund cancellation window, ~15-minute async completion, idempotency semantics for retries, and auth requirements. This is far beyond what the annotations 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?

Front-loaded with the core purpose, then flows through cost, auth, idempotency, and follow-up steps in a logical order. It is dense and mostly earns its place, though the long single paragraph packs slightly more than necessary for a first read.

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?

With no output schema, the description fully covers the return contract (a video_id returned right away, poll get_video, fetch share_url via status_tool once ready), plus timing, cost, and error/auth paths. Nothing an agent needs to call it correctly is missing.

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 already 100%, so the baseline is 3, but the description adds real meaning: it maps length to credit cost, explains brief should carry tone/audience, and clarifies idempotency_key is for retry safety. It stops short of documenting language/presenter enum sources beyond pointing to get_account.

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 (create a 9:16 AI UGC video ad for a website) with concrete output details (photoreal presenter, captions, brand colours), making it trivially distinguishable from siblings like get_video_sample and sign_in. An agent knows exactly what this produces.

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?

Explicitly covers when-to-use and gating conditions: checkout only when credits are insufficient, sign_in then retry when signed out, find-and-confirm URL for a business name with no URL, and poll get_video after. It names the sibling (sign_in) and the follow-up tool, leaving little to inference.

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