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

Annotations only state non-readOnly, non-idempotent, open-world. The description adds real behavioral facts not present in structured fields: the re-render preserves the same picture with a new take, it is FREE but limited to once per slide, and failed slides have already been refunded. The cost/quota constraint is exactly the kind of context annotations cannot carry.

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?

Two sentences, front-loaded with the action and the trigger, then the exclusion and cost. 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?

For a three-parameter mutation with no output schema and an annotation set that already declares safety and idempotency, the description covers the key unknowns: what gets changed (a fresh render, same picture), the cost model, and the failure-path alternative. It does not say what the call returns or whether the previous render is retained, which is a minor remaining gap.

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 description coverage is 100%, with job_id, slides (1-based, max 8) and user_goal all documented. The description only reinforces the per-slide scope through 'once per slide'; it adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 ('Render finished animated slides again — same picture, a new take') and pins down the scope: only slides that finished but whose motion is unsatisfactory. The contrast with the sibling tools animate_carousel and (implicitly) redo_carousel_slides is clear from the text alone.

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 the trigger condition ('when the motion came out wrong — the words wobbled, the character looked off') and an explicit exclusion with the correct alternative: slides that FAILED are already refunded and should go through animate_carousel instead. 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.