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

Annotations already establish read-only, idempotent, closed-world safety, and the description adds genuinely useful context beyond them: UK-only, free, validation-failure behaviour with no charge, and the coverage caveat that an empty answer may reflect missing data rather than absent sites. It also flags that the council's own figures take precedence over the calculated area. What it omits is operational behaviour: pagination via limit/cursor, default result counts, and ordering.

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 content is front-loaded — what it is, then what each site carries, then coverage caveat, then the single-scope rule — and every block carries information an agent needs. The raw line wrapping and an all-caps 'AS PUBLISHED' interrupt flow slightly, and the field inventory could be tightened, but there is no filler.

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?

An output schema exists, so return values need no explanation, and the description nonetheless states what each site record contains and where provenance comes from. It closes the biggest trap for this dataset (empty results may mean no coverage) and the validation/charging behaviour. The remaining gap is filter and pagination mechanics for the unfiltered-listing parameters, which a 13-parameter tool would benefit from.

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% across 13 parameters, so the description has to compensate and it partly does: radius_m is capped at 10 km, area_geojson is constrained to WGS84 red lines of at most 150 km² and 64 vertices, lpa_code is a GSS code with an example, and laa_positive is glossed as the council's suitable/available/achievable view. However, uses, kinds, statuses, min_units, min_area_ha, limit, cursor and include_geometry are never mentioned, and only a few enum members are explained, leaving substantial gaps for a 13-parameter tool.

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 opening sentence names a specific resource family — local plan site allocations, broad locations, SHLAA/HELAA/LAA sites and call-for-sites submissions — plus the two scoping modes (in an authority, or near a point). That vocabulary is distinct from the planning_applications, planning_designations and site_appraisal siblings, so an agent can route without opening the 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?

It gives an explicit hard constraint: supply exactly one of location/postcode/area_geojson/land_id/lpa_code, and anything else is refused before any read with no charge. It also warns that coverage `none` is not 'no sites'. It stops short of naming competing siblings (e.g. planning_applications, site_appraisal) and when to prefer them, so it is clear context rather than a full when/when-not ruling.

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