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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true), but the description adds substantive behavior beyond them: the idempotency mechanism (repeated identical requests with the same key return the original reference without duplicate delivery), the fact that a submission merely requests contact rather than confirming service, the external delivery to Formspree with the configured AI source, and the limitation that photos are not fetched. This is unusually complete behavioral disclosure for a write tool.

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?

Six sentences, front-loaded with what is created and where it is sent, then scope limits and return shape. It is dense but every sentence carries a distinct fact; the only minor waste is slight overlap with schema text on photos and preferred_date.

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 14 parameters, no output schema, and an external side effect, the description does the work the structured fields cannot: it states the return payload (reference, delivery status, call/text options), the idempotency contract, and the negative guarantees. An agent has everything needed to invoke it correctly and set expectations.

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 100%, so the schema already documents every parameter including the request_type/service enum guidance and the photo link caveat. The description's parameter-level statements (urgent_flood needs no preferred date, photos are optional HTTPS links) largely restate what the schema already says, so it adds little beyond the 3 baseline.

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 names a specific verb (creates/submits) and concrete resources (Premrest quote, preferred-date booking, urgent flood enquiry) and describes the full delivery path into the staff queue and Formspree inbox. This is clearly distinguishable from the read-only sibling list_services, which has no overlap in purpose.

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 gives a clear conditional rule for request_type selection ('urgent_flood requests use flood-restoration and do not require a preferred date') and states explicit scope exclusions ('does not confirm dispatch, arrival time, price or booking and does not process payments'). It does not, however, name an alternative tool to use when the request is not an enquiry, so routing guidance is context-rich but not complete.

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