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

Goes well past the annotations: policies are digitised so the caller should quote the council's reference and source rather than the returned wording, each layer reports its own coverage, and `not_held` explicitly does not mean the site lies outside a settlement — a genuine misinterpretation trap flagged. It also states pre-read validation (bad scope refused, nothing charged), the size/complexity caps on area_geojson, UK-only scope and that calls are free.

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-loaded with what the caller gets, then the sourcing caveat, then the scope rules and constraints — a sensible ordering with no filler sentences. It is dense and long-ish, but each clause conveys a distinct fact (layer coverage, not_held semantics, scope rules, limits).

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 five-parameter, multi-facet read tool with an output schema, the description covers sourcing, coverage semantics, validation behavior and limits thoroughly. The two gaps are the undocumented `themes` filter and the non-existent `lpa_code` argument, both of which would matter to an agent constructing a call.

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 0%, so the description carries the burden — and it does well for `location` ("lat,lng"), `postcode`, `area_geojson` (GeoJSON, WGS84, ≤150 km², ≤64 vertices), and `land_id`. However it never explains the `themes` parameter (a 10-value enum sitting in the schema with no documentation anywhere), and it advertises an `lpa_code` argument with a GSS example that does not exist in the input schema, which can send an agent down a failing path.

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 names the resource and enumerates the concrete payload: adopted/emerging local plan with stage and dates, covering policies with reference/theme/text extract/site share, settlement position with distance to edge, neighbourhood plans and green belt review rating. That is far more specific than the title alone. It never names a sibling (e.g. planning_designations, planning_check, constraints_for_geometry) to draw the boundary, so it stops short of a 5.

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?

Strong operational guidance: exactly one scope must be supplied, the accepted scope forms are listed, anything else is refused before any read with no charge, and the tool is UK-only and free. What is missing is when to reach for this tool versus the adjacent planning_designations / planning_check / constraints_for_geometry siblings, which an agent still has to infer from the subject matter.

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