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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds critical behavioral context: it emphasizes the tool is stateless and that page_onboarding_update does not remember earlier calls, requiring full resends. It also clarifies it does not create a page. No contradiction with annotations; the description enriches the behavioral picture significantly.

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 well-structured and front-loaded. The first sentence states purpose and non-create, the second gives the alternative, the third warns about statelessness, and the fourth gives the stopping condition. Every sentence adds value without redundancy.

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?

The description covers when to use the tool, when to stop, and the statelessness behavior, which are critical for correct invocation. Although it does not explain parameters, the output schema exists and the annotations cover safety. The main gap is parameter clarification, but the description is otherwise complete for decision-making.

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 description coverage is only 33%, with originalRequest lacking any description. The description does not explain the input parameters (locale, originalRequest, suggestedSelection) or how they map to the output choices. Since coverage is low, the description should compensate but does not, leaving agents uncertain about what to provide.

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 clearly states the tool's function: it returns category/layout/palette/primary-action choices and a quality checklist, and explicitly says it does NOT create a page. This distinguishes it from page_create_from_brief and other page creation tools. It also names the alternative flow, making it easy to differentiate among siblings.

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?

The description explicitly states when to use this tool ('Use it only if you want those pickers') and when not to ('otherwise page_intake_start → page_create_from_brief is the simpler path'). It also gives a concrete stopping condition: 'As soon as you have a business name and a primary action, stop and call page_create_from_brief.' This is excellent guidance.

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