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

Annotations only tell the agent this is a read-only, open-world, idempotent call; the description adds the real behavioral facts an agent needs — a 20-90 s runtime, the wait_seconds cutoff, and the partial-result contract (status 'running' plus an id). This is exactly the latency and long-running-call context annotations cannot express.

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?

Three tight sentences: what it does and returns, then timing, then the timeout branch. The most decision-relevant facts (free, real browser, return shape) are front-loaded 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?

No output schema exists, and the description fully covers the return shape including the alternate 'running' state, so an agent knows what to do in both the success and timeout cases. Nothing needed to invoke it correctly 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 already 100%, so baseline would be 3, but the description adds real meaning to wait_seconds by explaining its consequence (returning an id for get_report) rather than just its bound. The url parameter's public-site constraint is restated usefully but adds nothing beyond 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 ('Run a ... Site Check on a public website'), names the measurement method (real browser), and enumerates the returned payload (0-100 score, severity counts, top 5 problems, report URL). It also distinguishes itself from the sibling get_report by describing exactly when that tool becomes relevant (timeout).

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 clear operating context: free, public sites only, 20-90 s duration, and an explicit fallback path to get_report when wait_seconds elapses. It never explains when to prefer check_agent_ready over this tool, so sibling selection against that alternative is left to inference.

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