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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds the non-obvious behavioral trait that matters most here — STATELESS with no memory of prior calls — and explains the concrete consequence ('earlier choices will look missing'), which is exactly the kind of context annotations cannot convey.

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?

Front-loaded with the one-line purpose, then the STATELESS constraint and the routing hint in priority order. It is longer than average, but every sentence targets a distinct failure mode (dropped state, unnecessary looping), so the length is largely earned.

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?

With a nested schema, an output schema (covering return values), and informative annotations, the description supplies the critical missing piece — statelessness and full-state resubmission — plus the hand-off to page_create_from_brief. Minor gaps remain around stepId semantics and step progression, but nothing an agent needs to invoke it correctly is absent.

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?

Top-level schema coverage is only 25%, so the description must carry weight, and it does: it enumerates the accumulated selection fields (mainCategory, subCategory, layout, palette, primaryAction) and knownFields (name, description, action destination), and explains why full state must be resent. It omits stepId, locale, recommendedBlock, and the remaining knownFields flags, which are only partly documented in the schema.

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: 'Validate onboarding selections and return the remaining checklist.' This is clearly distinguishable from page_onboarding_start and names page_create_from_brief as the downstream tool, so an agent can place it in the flow without opening either schema.

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 explicit when-to-use instructions ('every call must include the FULL accumulated selection… plus all knownFields') and an explicit exit condition ('once you have a name and a primary action, call page_create_from_brief'). It even tells the agent not to loop to 'ready', removing a plausible wrong behavior.

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