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

Beyond the annotations (which already declare readOnly/idempotent/non-destructive/openWorld), the description discloses what is NOT checked (heritage, conservation, Article 4, landfill, policy), that failed counts remain unknown, that a low river/sea sample never means no flooding, and that source freshness and coverage are unverified. That is unusually rich behavioral context for a read tool.

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?

The Purpose/When/Returns/Limitations/Chaining structure is front-loaded and scannable, but the 'Returns' sentence partly duplicates an existing output schema, and the Limitations block is dense enough to be closer to a disclaimer wall than crisp guidance.

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?

With annotations, a full output schema, and complete parameter coverage already present, the description supplies the missing pieces: jurisdiction caveats, coverage limits, and chaining via site_ref. The only gap is the imprecise radius statement, which could mislead about account-tier limits.

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 description coverage is 100%, so the schema already carries parameter meaning; the description's 'full address/postcode, radius 250–1000m, optional focus' adds only marginal help. The radius guidance is also inconsistent with the schema, which allows up to 5000 with reductions to 1000/2000 depending on account, so the description understates the available range.

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 states a specific verb and resource ('prepare a limited first site read') and positions it as the initial entry point before other evidence tools. It is clear enough to distinguish from heavy siblings like prepare_site_research or site_verdict, though the phrase 'limited first site read' is somewhat abstract.

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?

Explicit when-to-use is given ('use for an initial resolved England address before selecting further evidence tools'), plus exclusions for Wales/Scotland and other countries. The 'Chaining' sentence tells the agent exactly what to do with the response next, with no inference required.

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