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

With annotations only declaring that this is a non-read, non-destructive write, the description carries real load: asynchronous 202 semantics, expected duration (~25 s to 2+ minutes), where the result lands (summary.lab.<strategy>, surfaced in GET /api/audits/:id, the tab and shared report), that the audit score is unaffected, in-flight deduplication, and concurrency/rate limits (4 concurrent, 6/network/hour, 500/day) plus cost (free, no x402 charge).

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?

Front-loading is good, but the text is substantially duplicated: the 202 response and ~25 s–2 min duration appear twice, and 'does not change the audit score' is stated twice in near-identical wording. Nearly half the text is restatement, so several sentences do not earn their place.

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 an async, rate-limited, no-output-schema tool, the description covers everything an agent needs: fire-and-forget semantics, where to retrieve results later, dedup behavior, limits and cost. Nothing material is missing and there is no output schema to compensate for.

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 67% and the description adds only indirect parameter context ('the same strategy', 'summary.lab.<strategy>'), while mobile/desktop semantics live in the schema itself. guest_token is undocumented everywhere. With most parameter meaning already in the schema, this lands at the baseline 3.

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 ('Starts a lab test of an audit's page') and immediately specifies the underlying engine and the four measured categories. It also names the sibling that consumes the result ('then read it with lab_result'), so an agent can distinguish it from lab_result and run_tab 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 clear sequencing guidance ('Answers 202 at once ... then read it with lab_result') and a conditional exclusion ('Calling again while the same strategy is running does not start a second test'). It does not compare against other test-running siblings like run_tab or watch_tab, so it stops short of full when-not-to-use guidance.

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