invariance_eval_experiment_run

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

Annotations already signal readOnlyHint=false and openWorldHint=true, so the description adds context beyond that: it states it 'Populates eval_results.scores' and 'records a baseline run'—concrete behavioral effects. It does not contradict the annotations and provides useful information about side effects and the baseline storage.

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?

The description is succinct and front-loaded: a single main sentence stating the purpose, immediately followed by the key details—the effect on eval_results.scores and a list of built-in scorers. No filler, every word contributes to understanding what the tool does and how to invoke it.

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 tool with no output schema, the description covers the essential inputs (id, body with required scorer_specs and optional baseline_run_id), the format of the body, and the built-in scorers with config hints. It could mention potential prerequisites (e.g., does the run need to be finished?) but the openWorldHint annotation somewhat accounts for unexpected side effects. Overall, it is sufficiently complete for an agent to make a correct call.

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 both parameters documented. The description adds significant extra meaning: it lists the built-in scorer names, explains the config.tolerance format for numeric_tolerance, and gives a concrete example of the body structure including baseline_run_id. This goes beyond the minimal schema description and helps the agent construct a valid request.

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 states a specific verb and resource: 'Execute an experiment against an existing eval run' and clarifies exactly what it does—applies scorer specs to every case result and optionally records a baseline run. It names the built-in scorers and the effect on eval_results.scores, which clearly distinguishes it from siblings like invariance_eval_suite_run or invariance_eval_experiment_compare.

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 clear context: you use this when you have an existing eval run and want to score its results with a list of scorer specs, optionally recording a baseline. It does not explicitly mention alternatives or when not to use it, but the purpose is unambiguous enough for an agent to pick it appropriately among the many sibling tools.

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