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

The readOnlyHint annotation covers the read-only behavior. The description adds the contextual requirement 'Requires project context' and clarifies the different output shapes (counts vs step results), which is useful beyond the annotation.

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 two sentences, directly addresses the primary use case and the alternative, and avoids unnecessary detail. Structure is clear and efficient.

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?

Covers purpose, parameter choice, and context requirement. Since there is no output schema, the description sufficiently hints at the return content (pass/fail counts, step results). A small omission is lack of mention of pagination defaults, but those are documented in the parameter descriptions.

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% and each parameter description already explains its purpose and constraints. The tool description largely reiterates the schema content (e.g., runId behavior) without adding new semantic detail beyond the schema, so a baseline score of 3 is appropriate.

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 the function: listing scenario runs with pass/fail counts, and also the alternative of retrieving a single run with step results via runId. This distinguishes it from other list_* tools like list_scenarios or list_test_runs.

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 explicit guidance on when to use runId vs scenarioId, stating runId returns one run's step results and makes scenarioId unneeded. Also notes 'Requires project context' as a prerequisite. Does not explicitly contrast with sibling tools, but the name and description are self-explanatory.

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