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

Annotations already mark readOnlyHint and idempotentHint, and the description reinforces 'Read-only; does not create a booking' and 'Showcase matching pros before any booking or OTP.' It adds non-obvious behavior: if the ZIP returns no providers, keep the empty result and do not substitute providers from another area. This is exactly the kind of context beyond annotations that helps an agent avoid a common mistake.

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 dense and every sentence carries information: use cases, exclusions, read-only status, ZIP handling, empty-result behavior, and context policy. It is longer than a one-liner but well organized with signposts. Slight redundancy with annotations (read-only) costs a point, though it is not enough to harm usability.

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?

Given the tool's moderate complexity — four parameters, one required, an optional analytics context field, and conditional ZIP sourcing — the description covers every operational aspect an agent needs: what triggers the call, what input to prefer, what to do on empty results, and what the read-only side effect is. The output schema exists, and the description properly avoids re-explaining return values.

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?

The schema has 50% description coverage, and the description compensates by explaining the location semantics ('Prefer a 5-digit US ZIP', 'Never pass a street address') and how to populate it after get_my_profile. The context parameter is also explained with length, person, and PII constraints. The page and limit parameters are not discussed in the description, but their integer defaults and idiomatic meaning are self-evident from the schema, so the compensation is adequate.

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 opens with a clear verb-resource pair ('find, search, or compare plumber professionals') and goes on to enumerate concrete scenarios (leaky faucet, clogged drain, water heater repair) that map directly to user intents. It is clearly differentiated from sibling find_electrician, find_hvac, and find_handyman tools by naming the plumber-specific domain.

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 states explicit when-to-use criteria (user wants plumber professionals or describes a plumber-solved problem) and explicit exclusions (DIY advice, cost research without hiring intent, auto/appliance retail, emergencies needing 911). It also provides a conditional branching rule involving get_my_profile and ZIP input, leaving no ambiguity about when this tool should be invoked over alternatives.

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