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

Annotations only declare readOnlyHint=true, so the description carries the rest and does add real context: date fields are matched as on-or-after with an explicit UTC format, and the archived/contact/deceased keys are mutually exclusive. That is meaningful operational behavior beyond the annotation. It omits rate limits and any note on result volume/pagination behavior.

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?

Front-loaded with the two examples before the long key enumeration, then the exclusion rule, then the API endpoint mapping. Dense but every clause carries information an agent needs to build a valid search payload.

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 nested, free-form search tool with no output schema, the description supplies the key vocabulary, date semantics, and mutual-exclusion rule, and pagination is documented in the schema. The remaining gap is that it never indicates which fields come back by default versus needing the 'fields' parameter, which matters when no output schema exists.

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 the baseline is 3, but the 'search' object is a free-form map whose allowed keys the schema cannot express, and the description enumerates all searchable keys plus the custom_<field id> convention and the on-or-after date semantics. That is substantive meaning added on top of 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 concrete verb+resource ('Find people matching field values') and immediately grounds it with two literal example payloads, so the agent knows exactly what input shape is expected. It does not, however, contrast itself with the sibling elvanto_list_people or elvanto_get_person, which is the only thing keeping this from a 5.

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 gives one genuine usage constraint ('Use only one of archived / contact / deceased at a time'), which prevents malformed calls. But it never says when to reach for this tool instead of elvanto_list_people or elvanto_get_person, so routing between siblings is left to inference.

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