invariance_eval_suite_run

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

The description adds behavioral context beyond the annotations: it executes every case and stores per-case results. It does not mention asynchronous behavior, what the caller receives after kickoff, or the full side-effect profile. The annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) are not contradicted.

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 wasted words. It states the action, the scope, the target kinds, and the outcome efficiently.

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?

Given the absence of an output schema and the moderately complex body parameter, the description is adequate but incomplete. It does not state what the tool returns, whether the run is asynchronous, or how to retrieve the stored per-case results, although sibling tools like invariance_eval_run_get and invariance_eval_run_results hint at those next steps.

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?

The description adds some semantic value by noting the target can be an agent, recipe, or inline override. However, the schema already documents the body parameter in detail, and the description does not clarify suite_id, metadata, case_ids, or the exact structure of an inline override.

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 ('Kick off an eval run') and resource ('suite'), and explains what happens: it executes every case against a target and stores per-case results. It is clear, though it does not explicitly differentiate itself from sibling run-related tools such as invariance_run_start or invariance_eval_experiment_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 implies when to use the tool: when you want to run a full eval suite against a target. However, it provides no explicit guidance about when not to use it, how it compares to alternative run/experiment tools, or what prerequisites exist beyond the suite_id.

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