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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the bar is lower. The description still adds real context: the sort order, the exact fields returned, the sensitivity of the data, and the underlying GET /customers/ endpoint. It omits truncation behavior, but the schema's limit param already warns that large replies are cut server-side.

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 short sentences, zero filler, with the resource, ordering, and field list front-loaded before the endpoint reference. Every phrase carries information.

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 read-only list tool with no output schema, the description supplies the return fields, ordering, and data-sensitivity note, and the schema handles pagination fully. Only the list-vs-search routing is left ambiguous.

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 each of page/limit/offset has a precise description including defaults, bounds, and the next_page/next_offset continuation pattern. The description adds nothing about pagination or params, so baseline 3 applies.

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+resource ('List customers') and enumerates the returned fields (name, email, phone, country, loyalty points, store credit) plus sort order (newest id first), which is well beyond a restatement of the title. It does not explicitly distinguish itself from hiboutik_search_customers or hiboutik_get_customer, leaving the list-vs-search-vs-fetch boundary to inference.

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?

No guidance on when to prefer this over hiboutik_search_customers (filtered lookup) or hiboutik_get_customer (single record). The only contextual note, 'Personal data of the shop's customers,' reads as a sensitivity flag rather than a usage rule.

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