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

The description discloses important non-obvious behaviors: it is STATELESS, requires resending the FULL set of selections + knownFields on update, and clearly states it does not create the page (consistent with readOnlyHint=true). It also adds a stopping condition, all of which go beyond what annotations provide.

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 a single dense paragraph of about 90 words packed with necessary information: purpose, alternatives, statelessness, and stopping rule. It is front-loaded but could be more scannable with bullet points. No sentence is wasted, though the structure is acceptable for the complexity.

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 purpose, usage conditions, alternatives, stateless behavior, and a clear exit criterion. Since an output schema exists, return-value details are already documented elsewhere. The description is sufficiently complete for the agent to select and invoke the tool correctly.

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 low (only locale has a top-level description; originalRequest has none, and suggestedSelection lacks a top-level description). The description references 'selections + knownFields' but does not explicitly map these to the schema's parameters, leaving originalRequest and suggestedSelection semantics under-specified. The nested schema partially documents subCategory and mainCategory, but the description does not compensate adequately for the gaps.

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 'returns category/layout/palette/primary-action choices and a quality checklist' and explicitly notes it 'does NOT create a page.' It differentiates from siblings by naming the alternative path 'page.intake.start → page.create_from_brief,' making it unambiguous when this helper is appropriate.

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 provides explicit usage guidance: 'Use it only if you want those pickers; otherwise page.intake.start → page.create_from_brief is the simpler path.' It also gives a concrete stopping rule: 'As soon as you have a business name and a primary action, stop and call page.create_from_brief,' which tells the agent exactly when to switch to a different tool.

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