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

Annotations already declare the safety profile (destructiveHint=false, openWorldHint=false, readOnlyHint=false), so the description only needs to add beyond them. The 'tested: no stat changes, ever' claim is genuine added context an agent couldn't infer from structured fields, but the description says nothing about persistence, whether the pet must exist, or how the change is confirmed. Note the annotations mark idempotentHint=false for what looks like a fixed-value setter, which the description neither explains nor contradicts.

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 one-liner, then WHEN, then the constraint, then the value source and example — a sensible order with no filler. The echoed example call largely restates the schema's required fields, so it is close to redundant but still helps as a formatting cue.

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?

A small, three-parameter tool with full annotation coverage and an output schema, so the description needn't explain return values or safety. It covers purpose, trigger, cosmetic constraint, and where to get valid values — the remaining gaps (preconditions such as owning a pet) are minor.

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 nominally 100%, but the per-parameter descriptions are boilerplate ('skin_color parameter for pet_skin') while the actual enums carry the information. The description's contribution is the pointer to pet_catalog as the source of valid values plus a call example, which is useful but does not explain the parameters themselves.

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 specific verb and resource ('change your pet's skin') and scopes it as cosmetic-only, which separates it from gameplay-affecting siblings like pet_feed or pet_teach. It doesn't explicitly name which sibling to use instead for non-cosmetic pet changes, so sibling differentiation is implied rather than stated.

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?

'WHEN: change your pet's skin' gives an explicit trigger, and 'Pick any color/pattern from pet_catalog' routes the agent to the prerequisite lookup tool. There is no explicit when-not guidance, but the 'COSMETIC ONLY' line heads off the main wrong expectation (stat effects).

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