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

Annotations are sparse (readOnlyHint=false, openWorldHint=true), so the description carries real weight and delivers: per-scenario credit spend, a credit check before any member starts, shared launch concurrency, requestId deduplication, and the exact result shape ('id, status, cause, timestamps, and report link, not the full run record'). This is disclosure well beyond what the annotations provide.

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?

Core purpose and constraints are front-loaded before the operational details, and most sentences earn their place. Some redundancy exists, notably the requestId dedup and wait-budget explanations, which restate what the schema fields already say.

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 12-parameter mutation tool with no output schema, the description covers everything an agent needs: preconditions, credit behavior, dedup, wait-budget exhaustion handling, next-tool routing, and the shape of the returned result. No material gap remains.

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 75%, so the baseline sits at 3; the description adds genuine meaning on top by explaining the suite membership constraint and why one would 'Pass baseUrl to test a preview deployment.' Several parameters (pr, live, branch, commitSha, requireVerified) get no description-level treatment, and the requestId explanation largely restates the schema.

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?

States a specific verb and resource with an explicit scope limit: 'Run the newest 20 saved scenarios in one project, or one named suite, and wait for the verdicts.' The project-vs-suite-vs-single-scenario distinction is unambiguous, letting an agent separate it from run_scenario without opening either schema.

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?

Gives explicit when-to-use context plus named alternatives and next steps: 'call wait_for_run with each pending run id and do not launch again' and 'Call get_run for evidence.' It also states exclusions ('Unsaved checks are not included') and rejection preconditions ('A suite runs only when every member is among those 20').

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