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

No annotations exist, so the description carries the full burden and mostly succeeds: it discloses the data providers, that `bati` resolves the parcel first then sums BDTOPO buildings by centroid, that `bati` returns an `error` key when no parcel is found, that `solaire` returns physical data only with no tariff assumptions, and that `parcelle`/`adresse` may return null. It omits latency, caching, and licensing/mutation profile, but the read-only nature is implicit in a point lookup.

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 one-line summary followed by a prerequisite hint and four tight per-op bullets — a good dispatcher layout. Slightly verbose within the bullets (e.g. the CES interpretation aside), but every clause carries actionable information and 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?

For a four-mode tool this is close to complete: each op's resolution logic, its failure mode (null vs `error` key), and its output vocabulary are covered. The platform-level parameters (_org, _group, _project, _run_id, _instance) are not addressed at all, though they are documented in the schema; an output schema exists, so omitted return-shape detail is acceptable.

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%, so the baseline is 3, but the description genuinely adds meaning beyond the schema: the enum values are expanded into full behavioral contracts and `kwc` is described as 'REQUIRED for that op, ignored by the others', including that it drives the PVGIS sizing at optimal tilt/azimuth. That is more than restating the enum list.

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 precise verb+resource statement — what a (lat, lon) point resolves to — and enumerates the four concrete artifacts (cadastral parcel, built footprint, nearest address, solar yield). Each `op` value is then named with its upstream source (API Carto IGN, BDTOPO V3, PVGIS JRC, BAN), so an agent can distinguish it from siblings like foncier_geocode or foncier_dvf 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?

Explicitly states the prerequisite chain ('Geocode the address first (foncier_geocode)') and gives per-op rationale — 'Use to identify the land unit under an address' and 'low CES in a dense area = under-developed land signal'. It stops short of naming when NOT to use it or pointing at sibling alternatives (e.g. foncier_dvf for values, foncier_permis_search for planning), so the routing guidance is clear but not exclusionary.

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