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

readOnlyHint=true already covers the safety profile, so the description adds value by disclosing what comes back (contact data, addresses, balances, consents) and the underlying endpoint GET /clients/clients. It does not explain matching semantics for text search or pagination defaults, which keeps it below a 5.

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 compact sentences, front-loaded with the primary capability followed by return contents and endpoint, with no filler or redundancy.

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 all five parameters documented at 100% coverage and no output schema, the description's return-value summary plus endpoint reference covers most of what an agent needs. Missing details are minor: pagination defaults and how multiple filters combine.

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 baseline is 3; the description earns a bump by clarifying that text matches name, e-mail and login, which the schema only describes vaguely as 'Text searched in customer data'. It does not add anything about limit/page or the customer_ids array beyond the schema.

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 (Find) and resource (customer accounts) and enumerates the three filter modes: text, ids, active state. The resource is clearly distinct from siblings like search_orders and search_products, though it doesn't explicitly name the boundary against them.

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?

Usage is implied by the enumeration of filter modes (text over name/e-mail/login, ids, active state), so an agent can infer the common call patterns. However, there is no explicit when-to-use versus alternatives, no note that all parameters are optional, and no guidance on combining filters.

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