Collect a running measurement

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses that calls always return immediately (non-blocking poll), that clients enforce a hard wall-clock limit that progress notifications do not extend, and why long measurements must be deferred to a job. It also explains the underlying latency source (Google re-analysing the URL roughly once a minute), which prevents fruitless retry loops.

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?

Use case and polling cadence are front-loaded, and every sentence carries operational information. There is mild redundancy — the wall-clock explanation and the 'does not make it arrive any sooner' sentence overlap in conveying 'wait for it, don't restart' — plus a capitalized emphasis that could be tightened.

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 compensates by defining the return value ('exactly what the tool would have returned'). For a one-optional-parameter, read-only polling tool, the description covers purpose, timing, defaults, failure modes, and return semantics with nothing an agent needs left out.

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 the single optional job_id is already documented in the schema, so the baseline would be 3. The description adds real meaning by identifying the provenance of the value ('handed back as a job id' by analyse_page or compare_to_baseline) and restating the omit-for-latest default in behavioral context.

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 — collect the result of a measurement job — and names the two sibling tools (analyse_page, compare_to_baseline) whose job ids it consumes. It also clarifies the return contract ('returns exactly what the tool would have returned'), so an agent knows this is a completion/collection step, not a new analysis.

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 polling cadence ('about every 15 seconds until it reports done'), an explicit default ('omit job_id for the most recent job'), and an explicit anti-pattern ('starting the same measurement again while one is running does not make it arrive any sooner'). The when-to-use chain from analyse_page/compare_to_baseline is spelled out rather than inferred.

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