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

readOnlyHint=true is the only annotation, and the description corroborates it by framing this as a rendering pass performed 'before creating', with an explicit return payload: screenshots plus lint on contrast, long labels and missing help. It does not address whether the preview is persisted or expires, which is the one remaining behavioral gap.

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 what is rendered and returned, then the input scoping, then the workflow guidance. Dense but every clause carries information an agent needs.

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 read-only tool with 10 parameters and no output schema, the description covers the return artifacts, the input subset and the workflow, which is enough to call it correctly. Minor gaps are lifetime/persistence of the preview and any auth requirement, neither of which blocks a correct call.

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 60%, and the description usefully clarifies that this accepts the fields of createRequest minus audience, expiresIn, webhookUrl and metadata — a scoping rule the schema cannot express on its own. It also names viewports and sampleData and their purpose, going beyond the property definitions.

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 — renders the form or approval card as a recipient sees it — and pins down the output (screenshots plus plain-language lint) and the two viewport widths. An agent can distinguish this from createRequest purely from the text, since 'preview' versus 'create' is drawn explicitly.

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 an explicit trigger ('preview before creating when the person will see the form more than once') and an implicit exclusion for one-off forms, plus the follow-up action ('then adjust theme and hints'). It also names the sibling it relates to (createRequest) and the fields to reuse.

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