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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds the crucial statelessness trait: 'STATELESS: it does not remember previous calls'. It also explains the consequence of omitting earlier selections, going beyond annotation coverage.

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?

The description is 3 sentences (~100 words) and front-loaded with the core action. The STATELESS warning and loop exit condition are essential context, though the prose is somewhat dense.

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?

Given the tool's 4-parameter, nested-object schema and output schema, the description covers critical behavioral requirements: full payload, no state, and handoff to page.create_from_brief. It doesn't explain stepId or selection semantics, but the schema handles those.

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?

The description lists the required accumulated fields (mainCategory, subCategory, layout, palette, primaryAction) and knownFields, adding the key semantic that all must be sent together. While it doesn't define each parameter's value, the input schema provides enums/descriptions for some nested fields.

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 opens with 'Validate onboarding selections and return the remaining checklist', a specific verb and clear resource. It also references page.create_from_brief as the follow-up step, distinguishing itself from page creation tools.

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 warns against looping: 'You do not need to loop to a "ready" state' and instructs to call page.create_from_brief once name and primary action are available. It also mandates including the full accumulated selection every call, providing concrete usage guidance.

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