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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds the non-obvious behavioral constraint that Smaregi cannot search by name/phone/e-mail and flags that the payload contains shoppers' personal data. No mention of rate limits or reply size limits beyond what the schema states.

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?

Three tight sentences: returned fields first, then the search constraints and alternatives, then the PII caveat. Every sentence carries actionable information with no padding.

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 and 100% schema coverage on ten optional params, the description supplies the missing pieces: what is returned, how to filter given the name/phone limitation, and a data-sensitivity warning. Nothing essential for a correct first call is absent.

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%, so 3 is the baseline; the description earns an extra point by explaining the intended filtering strategy (code, member number, id range, update time, pagination) that a caller would otherwise have to infer by reading all ten property descriptions. It adds strategy, not syntax, but that strategy is the piece the schema lacks.

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 specific verb and resource plus the exact fields returned (id, code, name, phone, e-mail, address) and the underlying endpoint GET /customers, so the agent knows precisely what comes back. It does not, however, acknowledge the sibling smaregi_get_customer, which overlaps with the single-record filter modes it describes.

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 rules out searching by name, phone or e-mail and redirects to the supported filters (customer code, member number, id range, update time) or paging — a clear 'how to use' instruction that prevents failed attempts. No explicit when-not condition vs. get_customer, so it stops short of a 5.

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