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

The annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds valuable context beyond that by clarifying that 'evals' are canned mock-conversation scenarios and by noting the API mirror ('GET /api/v1/evals'), which helps the agent understand the nature and scope of the operation.

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 sentences contain the essential purpose, scope, and API correspondence with no filler. The primary action and resource are front-loaded, making the intent immediately clear.

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 simple, optional-filter list tool, the description plus schema and annotations cover what an agent needs: the resource type, the filtering behavior, and the safety profile. The output schema is present, so return-value documentation is handled structurally. It could mention pagination or permissions, but these are minor against the low complexity.

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 for the single parameter is 100%, so the baseline is 3. The description adds meaningful nuance by stating that omitting agent_id returns all accessible agents, which the schema's 'optional' wording does not fully convey. This enriches the parameter semantics beyond the schema alone.

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 uses a specific verb ('List') and a specific resource ('canned mock-conversation eval scenarios'), with clear scoping ('for an agent (or all accessible agents)'). This distinguishes it from siblings like run_eval, which would execute rather than list evals.

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 clearly implies when to use the tool: when you need to view predefined eval scenarios rather than run them. However, it does not explicitly name run_eval as the alternative or state when-not-to-use, leaving the routing to inference from the sibling list.

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