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

Annotations already declare idempotentHint=true and destructiveHint=false, so the description's key contribution is the cost model — that generation draws down the signed-in account's existing credits — plus the fact that a private project is created as a side effect and that share links are conditional. That is meaningful context beyond the annotations, though return shape and credit-failure behavior are unaddressed.

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?

Three sentences, front-loaded with the action and its side effects, with no filler. Minor redundancy in restating requestId reuse guidance that the schema already carries, but it is placed where an agent scanning the description will see it.

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 6-parameter mutation with no output schema, the description covers the essentials: what is produced, what it costs, what gets persisted, and the idempotency contract. It stops short of describing what a successful response contains or how credit exhaustion surfaces, which are the only notable gaps.

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?

With schema coverage at 33%, the description compensates only for requestId (new per generation, reused on retry) and share (link only when true), both of which the schema already documents. The three remaining parameters — style, title, vehicleId — plus the free-text description field get no semantic help from the description, so the compensation is partial.

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 names a specific verb (generate), the resource (a wrap image), the mechanism (site image pipeline), and the two side effects (consume credits, save a private project). It is clear what the tool does, though it never names sibling create_project_from_image or explains how they differ, leaving differentiation to inference.

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?

Usage guidance is limited to the requestId lifecycle (new id per generation, reuse on retry) and the share-true condition for links. It does not say when this tool should be chosen over create_project_from_image or whether get_wrap_prompt should be called first, so the when-to-use decision is implied rather than stated.

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