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

Annotations declare openWorldHint=true and idempotentHint=false, and the description earns its place by adding the callback SLA (within the hour, business hours), the zero-cost framing, and that a reference is returned. It omits the practical consequence of non-idempotency — that resubmitting likely creates a duplicate dispatch — and says nothing about PII handling for name/phone.

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?

Short and front-loaded, with the consent and area constraints leading and the ZIP pre-check last. The parenthetical '(a vetted local pro calls back within the hour during business hours)' redundantly restates the callback already named in the preceding clause, which is wasted text.

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 a 7-parameter mutation tool with no output schema, the description covers cost, callback timing, consent, area validation, and the shape of the return ('a reference and what happens next'). Missing only duplicate-submission and cancellation expectations, which an agent scheduling a real-world dispatch would want.

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 every parameter including optional email, language, and preferred_time is self-documenting; baseline 3 applies. The description only adds meaning for zip (validate first) and name/consent, leaving need, phone, and scheduling fields entirely to 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 concrete verb and resource (book backflow testing), scopes it geographically (Charleston area), and adds the precondition of a real person with consent. It also implicitly distinguishes itself from check_service_area, which handles ZIP validation rather than booking.

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?

Explicitly routes the agent to the sibling: 'Check the ZIP with check_service_area first if unsure,' and constrains use to a person who asked for it with consent. It never states when not to book or what to do on repeat requests, so it's strong but not exhaustive.

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