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

Beyond annotations it discloses critical behavior: failed sources return unknown counts not zero, national origin/council coverage/freshness unverified, no implied approval or absence of applications. These are exactly the caveats an agent needs to interpret results correctly.

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?

Labeled sections (Purpose/When/Returns/Limitations/Parameter guidance/Chaining) front-load the essentials with no filler, though the single-block density is longer than strictly necessary.

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?

Covers purpose, caveats, parameter ranges, and chaining even though an output schema exists. Nothing an agent needs to call this correctly or interpret its limits 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?

With 40% schema coverage the description compensates well: radius 250–1000m, limit 1–20, optional outcome filter, and the key nuance that filtering applies only to the returned bounded sample. It also steers address vs site_ref choice, though it doesn't explain each site_ref field.

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+resource with explicit scope: 'retrieve a bounded national planning-application sample for a resolved England site.' The bounded/sample/England qualifiers clearly separate it from siblings like find_precedents or get_local_plan_policies.

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?

'When to use' plus limitations carve out clear conditions: first-pass record research, local-portal verification required, non-England jurisdictions out of scope. Strong, though it does not explicitly name a sibling alternative the way an ideal 5 would.

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