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

Annotations only declare the generic profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description carries most of the weight and does well: it discloses cost ("FREE"), that the operation has a side effect of drawing/reusing a character, that redraw is limited to a few per carousel, and the required approval gate before rendering. What it omits is failure behavior (unknown job_id, mismatched slides) and whether the returned frames are cached between calls.

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?

It is front-loaded with the two facts an agent needs first — that it is free and that it precedes animate_carousel — and every clause adds operative information. It is dense rather than wasteful, though the single packed paragraph with nested parentheticals could be split for scanability.

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 5-param tool with a nested `slides` object and no output schema, the description covers inputs, the returned artifacts, cost, and the workflow handoff to the rendering sibling. Missing only edge-case behavior (invalid job_id, exceeds-redraw-limit response) and confirmation that the preview is cached so the render step reuses exactly these frames.

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; the description earns an extra point by explaining cross-tool semantics the schema cannot: `slides` must be the same set later passed to animate_carousel, and `character` accepts a `saved_character_id`, a `description`, or a `reference_url` and matters when a slide is `pass_through`. `user_goal` and `job_id` are left entirely to the schema, which is acceptable given full coverage.

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?

The description states a concrete verb and resource: it draws or reuses the walk-through character, returns three poses, and produces each moving slide's `start_image`/`end_image` with the character placed. It also positions itself unambiguously as the step before animate_carousel, which is the nearest sibling, so an agent can distinguish the two without opening either 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?

It explicitly names the prerequisite relationship ("Before animate_carousel"), the exact handoff ("Send the same `slides` you will animate"), and the follow-up ("get the owner's OK on the price in the answer, then call animate_carousel with the same slides"). It also bounds the `redraw` option ("a few per carousel"), which is the only real usage choice in the tool.

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