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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile needs no repetition. The description adds nothing beyond those annotations: no pagination behavior, no filtering semantics for the free-form query object, no note on what is returned.

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?

Extremely short but wasteful: the identical route string appears twice, and the operation ID hash adds no informational value to an agent choosing a tool. Size is fine, but the content is duplicated rather than front-loaded with meaning.

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?

No output schema exists, so the description should describe the returned collection and how the free-form query filters it; it does neither. For a 2-parameter nested-object tool with 0% schema coverage, an agent cannot call this confidently beyond passing a siteId.

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 0% and the description supplies no parameter meaning at all. The required siteId is only inferable from the raw path text, and the open-ended 'query' object (arbitrary additional properties) is completely undocumented — exactly the case where the description is supposed to compensate.

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 simply restates the HTTP route and title verbatim ('GET /api/sites/:siteId/contacts'), so the only purpose signal is the endpoint path itself. An agent can infer it lists contacts for a site, but nothing states what a contact record is, why it differs from get_contacts or get_sites_by_siteId_units, or what the response contains.

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 when-to-use, when-not, or sibling differentiation is given, despite dozens of closely related project/contact/site endpoints in the sibling list. The only actionable pointer is that describe_operation provides native request schemas, which is schema guidance rather than usage guidance.

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