list_runs

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

No annotations provided, so description carries the burden. It discloses that the tool returns run_id, status, tags but does not mention pagination behavior despite schema having page_size/page_token. It implies a safe read operation but does not explicitly state read-only nature.

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 conveying purpose, composition, return fields, and a usage example. No wasted words, efficient and to the point.

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?

Lacks output schema; description partially explains return values (run_id, status, tags) but omits other potential fields. Pagination is not explicitly described despite being in schema. For a list tool, more context on pagination and sorting would improve completeness.

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% with descriptions for all parameters. The description adds a concrete filter example that goes beyond schema, aiding understanding. However, it does not elaborate on other parameters like order_by or page_token.

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 clearly states 'List evaluation runs' and defines what constitutes a run (agent + persona + test_set). It distinguishes from sibling list_* tools by specifying the resource and the information returned (run_id, status, tags).

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?

Provides a concrete filtering example with filter='tag="regression"' which guides usage of the filter parameter. However, it lacks explicit guidance on when to use this tool versus other list tools or when not to use it.

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