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 is covered. The description adds one genuinely useful trait beyond them: the cursor is described as "stable," telling the agent that pagination ordering will not shift between pages. It gives no information on ordering key, page size behavior, or what an empty result implies.

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?

A single front-loaded sentence with no filler; the resource and the pagination trait come first. It is arguably under-specified rather than over-long, but nothing in it is wasted.

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?

The output schema exists and the annotations plus full schema coverage carry the parameter and safety burden, so the description need not explain return shape. It is still thin for a tool with three sibling list operations, since it never says what an evaluation is or how this list differs from runs.list.

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 100%, with limit bounds, enum values for status, and cursor provenance all documented in the schema itself. The description only echoes cursor and adds no format, ordering, or interaction detail beyond it, so the baseline of 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?

The description names a specific verb ("List") and resource ("evaluations") and scopes it to the organization, so an agent knows exactly what it returns. It does not differentiate from the sibling runs.list, which is also a paginated list operation, leaving the reader to infer that the resources differ only by name.

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?

There is no statement of when to use this rather than runs.list or docs.search, no prerequisite/auth conditions, and no mention of the status filter as a selection mechanism. The only usable guidance is the implicit "listing" semantics of the name.

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