list_customers

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description notes '[tier: readonly-owner]' which hints at access level, but doesn't explain what this means behaviorally. There's no mention of pagination behavior, default page size, rate limits, or what happens when no customers match. For a list tool, the description is thin on behavioral detail beyond 'it lists.'

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?

Two sentences, zero waste. It states the core function (list customers), lists the key options (optional search, sorting, pagination), and adds the endpoint mapping for technical grounding. This is appropriately concise and front-loaded with the core purpose.

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 list tool with 6 parameters and no output schema, the description is somewhat minimal. It covers the three main operations (search, sort, paginate) but doesn't explain default behaviors (e.g., default sort order, default page size), the expand parameter's effect on response size, or the meaning of 'readonly-owner' tier. Given no output schema and no annotations, the description could do more.

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 50%, meaning half the parameters have descriptions in the schema. The description itself mentions search, sorting, and pagination, which loosely maps to q, sort_by/sort_direction, and page/page_size parameters. However, it adds no detail beyond what the schema provides for those parameters, and the undocumented parameters (page, sort_direction) get no additional explanation. The description doesn't compensate for the coverage gap, staying at 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 clearly states what the tool does: 'List customers, with optional search, sorting and pagination.' It uses a specific verb (list) plus resource (customers) and mentions the HTTP endpoint mapping. It's clearly distinct from siblings like get_customer (single record) and list_customer_addresses (different resource). However, it doesn't differentiate itself from the other list_* sibling tools beyond naming the resource, but that's inherent to the naming.

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?

The description mentions optional search, sorting and pagination, giving some implicit guidance on when these features are used. However, it doesn't explicitly state when to use this vs alternatives (like get_customer for a single record, or list_customer_addresses for addresses). No exclusions or prerequisites (e.g., ownership constraints) are noted. The guidance is adequate but implicit.

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