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

Annotations only mark this as non-read-only, non-idempotent, open-world; the description adds materially more: it spends credits, requestId replays the earlier launch without charging again, wait=false returns an id with done=false, the wait budget may expire, and it clarifies verdict semantics ('failed means a bug was found; error is not a product verdict').

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?

Purpose and cost warning are front-loaded, then routing, parameters, and return/follow-up behavior in a logical order. It is dense and runs long, but nearly every clause carries operational information (credits, idempotency, resume path), so little is waste.

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?

With no output schema, the description carries the return contract itself: done, run (status, bugReportsCount, creditsCharged), and reportUrl, plus the follow-up chain to get_run, get_screenshot via run.sessionId and evidence.screenshots fileName, and wait_for_run. Nothing needed to invoke or interpret the result is missing.

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%, so the schema already documents all seven parameters and the baseline would be 3. The description still adds value by scoping environment to the exact name on that scenario's project, tying requestId to the charge-avoidance behavior, and explaining live as skipping a recorded path and timeoutSeconds as capped by the server's per-call budget.

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 concrete verb+resource+scope ('Run one saved scenario in Chromium', one scenarioId, waits for verdict by default). It explicitly distinguishes itself from the two nearest siblings, check and run_project, so an agent can route 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 routing: list_scenarios to obtain scenarioId, check when you have a URL and expectation instead of a saved scenario, run_project for the newest 20 or a suite. Also states what to do on non-completion (wait_for_run) and after completion (get_run, then get_screenshot).

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