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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description goes well beyond them: roughly one-minute latency, 24-hour per-domain result caching, and a stated blind spot for server-side or consent-gated tracking. Those three facts directly affect whether an agent should re-run the tool or how it should phrase results.

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?

Five short sentences, front-loaded with what it does, then when to use it, then latency, caching, and the caveat. No sentence is filler; each one changes how an agent would call or report on the tool.

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 a one-parameter, no-output-schema tool, the description covers cost (time), freshness (cache), and interpretation risk (invisible setups) — the three things an agent needs to call it responsibly and describe results accurately.

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% with a single documented `url` parameter, so the schema carries parameter semantics. The description adds only the implicit constraint that the target must be a public page, which is useful but marginal — baseline 3 applies.

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?

Opens with a specific verb+resource pair: loads one public web page in a real browser and reports analytics/ad conversion tag status. The three-way outcome split (seen / not seen / unverifiable) tells an agent exactly what kind of answer to expect.

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?

"Use when someone asks whether a business website's tracking is set up" gives a concrete trigger, and the false-negative caveat about server-side or consent-gated setups sets an important boundary on interpretation. No sibling tools exist to route to, so the missing alternative-naming does not cost much.

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