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

Goes well past the annotations (which only say non-readOnly, idempotent, non-destructive) by disclosing the per-call cost ($0.001), that failures are free, that each answer set is persisted, and that a calendar.routed event fires — genuinely useful side-effect information an agent cannot get from structured fields. The partial-update rule ('only the fields you pass change') also reinforces and sharpens the idempotentHint.

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?

Dense and front-loaded: the core action comes first, followed by routing semantics, URL, then cost/side effects. Nearly every sentence carries information, though the single long block is heavy and could be split for faster scanning.

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 an 8-parameter, nested-object mutation with no output schema, the description supplies the conceptual model (questions → routes → fallback), the update semantics, the resulting address, the cost, and the emitted event — everything an agent needs to call it correctly without guessing.

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?

With 63% schema coverage and deeply nested routes/fallback/questions, the description earns its keep by explaining route evaluation ('first route whose conditions all hold wins; everyone else takes the fallback') and the special meaning of name/email question keys pre-filling the booking form. It does not explain the simple fields title, active, person, or description, so it is not fully compensating for the coverage gap.

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?

Opens with a specific verb+resource ('Create or change a routing form') and then defines the resource concretely — questions, routes, fallback, URL shape — so it is unmistakably distinct from calendar_list_routing_forms, calendar_save_meeting_type, and forms_create. An agent knows exactly what it is saving and where it appears.

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 makes the create-or-update semantics explicit ('Only the fields you pass change') and points to calendar_list_routing_responses for answer sets and the calendar.routed event for downstream consumers, which gives clear situational context. It does not, however, state when to prefer this over building a plain booking flow or an alternative form tool, so it falls short of the explicit when/when-not bar.

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