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

Goes well beyond the annotations: discloses that the job is paid and requires user approval, that requestId deduplicates identical retries for 24h, the explicit rule against minting a new id after an uncertain outcome, and that it returns taskId. This is exactly the destructive/monetary context an agent needs before firing a write.

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 dense sentences, front-loaded with the monetary/approval fact, then the retry rule, then the return value, then the i2v/t2v routing. Nothing is repeated from the schema or annotations.

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 an 11-parameter paid mutation with no output schema, the description nails the safety and retry story but leaves the majority of parameters and the valid duration/resolution domain unexplained. It's adequate to call safely but not complete enough to call optimally.

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 only 18%, so the description must carry the load, and it only clarifies requestId dedup semantics, expectedCredits, and the model naming convention. undefined behavior for duration, resolution, aspectRatio, audio, multiShots, lastFrameUrl, and prompt remains with no explanation in either place.

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?

Specific verb+resource ('Start a paid video job') with the key distinguishing attributes (paid, approval-gated, expectedCredits quote) stated up front. An agent can separate this from estimate_video_cost, get_video_status, and upload_image without opening any schema.

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 routes the i2v path through upload_image first and the t2v path through a '-t2v' model, which is real when-to-use guidance tied to siblings. It doesn't state preconditions like needing a quote from estimate_video_cost or sufficient balance, so it stops short of full routing coverage.

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