Run an evaluation

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

With no annotations, the description carries the full burden. It discloses that running counts against a 20-run-per-agent-per-24h limit and requires confirm: true, which is important operational guidance. It also mentions the optional wait-for-summary behavior, though it does not explain what is returned when wait is false.

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 tight sentences, front-loaded with the core action and immediately followed by the most important caveats. Every clause adds information: test set target, draft/published default, optional waiting, and quota/confirm requirement.

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 description covers the key action and constraints but has gaps: it does not describe the return value when wait is false, does not mention how to poll for results via cs_get_evaluation_run, and does not explain the dry-run behavior when confirm is false. Given 12 parameters and no output schema, a complete definition should provide more guidance.

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 58%, so the schema already documents many parameters, but the description adds meaning missing from the schema for runOnPublishedBot ('draft agent by default, or the published one'), wait ('Optionally wait for completion'), and confirm ('requires confirm: true'). This goes beyond the bare schema and helps parameter selection.

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?

Description states a specific action ('Start an evaluation run') on a specific resource (a test set) and clarifies the draft-agent default vs the published one. It clearly differentiates from siblings like cs_get_evaluation_run and cs_list_evaluation_runs by focusing on initiating a run.

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 useful context like the optional wait behavior and the 20-run quota, but it does not explicitly say when to use this tool over alternatives or when not to use it. It implies usage for starting evaluation runs but leaves the choice versus cs_run_conversation_tests or polling tools to the agent.

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