Search customers

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds useful behavior context, such as partial matching and returned fields, but it doesn't describe ordering, pagination, or how the limit parameter affects results.

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 three short sentences with no filler. It front-loads the core search behavior, then states the output and the practical use case, making every sentence earn its place.

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 no output schema, the description usefully lists return fields and gives explicit workflow context. It covers the required query input and the duplicate-avoidance purpose, though it omits minor details like result ordering and whether results are paginated.

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 documents the query parameter's meaning and the limit's constraints, and the description reinforces that query is a name, email, or phone fragment. However, the description doesn't add semantic detail for the limit parameter beyond what the schema already provides.

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 uses a specific verb and resource: 'Find customers by part of their name, email or phone.' It clearly defines the search scope and lists the returned fields, making the tool's purpose distinct from siblings like get_customer.

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 explicitly advises using this tool before creating a customer to avoid duplicates, which is clear contextual guidance. It doesn't mention alternatives or when not to use it, but the primary workflow is well established.

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