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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description adds substantial behavior beyond that: the 5-match cap, the presence of a guidance line, cross-brand search semantics (same name in two brands = two customers), and the locations array ordering with primary first.

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?

Purpose is front-loaded and every sentence carries a distinct rule (matching, cap, disambiguation, brand, locations). It is dense and slightly run-on across six clauses, but no sentence is filler.

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 no output schema, the description still conveys the shape of the result (matches, guidance, brand, locations with primary first), so an agent knows what to expect and how to act on it. Nothing needed to call this correctly is missing.

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 coverage is 100% and the single param is already documented as accepting any fragment. The description still adds value the schema does not: phone numbers match regardless of formatting, and the query spans name/phone/email/postcode uniformly.

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?

Names a specific verb (look up) and resource (customer) plus the accepted search key types (name, phone, email, postcode). It is clearly distinguishable from siblings like find_project, find_resource, and search, which are not described with this customer-centric matching scope.

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 instructs how to behave on multi-match results ('tell the user who matched and ask which they mean - never pick one yourself') and routes the agent onward to create_job when a site is named. It also tells the agent to follow the returned guidance line, which is a concrete when-to-do-what rule.

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