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

Annotations already establish a safe, idempotent, read-only poll, lowering the bar, but the description still adds real behavioral context: no credit spend, a server-capped per-call budget, the semantic split between failed (bug found) and error (not a product verdict), and the resume path (done false plus resume.tool) when the budget expires. The only gap is pagination/partial-result timing beyond the budget case.

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 the negative scope are front-loaded in the first two sentences, then required vs optional parameters, verdict semantics, and the resume instruction follow in a logical order. Despite its length, every sentence carries routing, parameter, or return-behavior information with no filler.

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?

There is no output schema, so the description carries the full return burden and does so: done true with run and reportUrl on passed/failed/error, done false with status and resume.tool on budget exhaustion, and the requireVerified verification object. An agent knows both how to call it and what shapes to expect.

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 runId, timeoutSeconds (including the server budget cap), and requireVerified. The description still adds workflow meaning the schema lacks: runId must come from the specific launch, and requireVerified 'adds a verification object when every required outcome passed with current evidence,' clarifying its return-level effect rather than just its boolean meaning.

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 names a specific verb and resource ('Wait for a run already started by ... then return its verdict') and immediately draws the boundary against siblings with 'Does not spend credits or start a run,' which separates it from run_scenario, run_project, and check. An agent can select this tool without opening any 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?

It gives explicit call conditions ('Call once per runId when several runs are in progress, including each pending id from run_project'), prerequisites ('Required: runId from that launch'), and routes to named alternatives for adjacent needs (get_run for bug reports, get_screenshot for evidence files). Both when-to-use and when-to-go-elsewhere are covered.

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