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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-obvious semantics: headroom is the operator's heat-map figure on its file date, not a connection offer, and a null headroom never means 'no capacity'. It also discloses validation-before-read behavior, cost ('Free'), and GB-only coverage — exactly the context annotations cannot carry.

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-loads what the agent gets, then the critical headroom caveat, then the invocation rule — a good priority order. It is dense and slightly run-on in the parenthetical scope list, but every clause carries information; nothing is 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 covers the interpretive traps that would otherwise cause misreads. Remaining gaps are the unmentioned radius/limit defaults and headroom filter semantics, plus the schema/description mismatch on `lpa_code`.

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 0% schema description coverage the description must carry all eight parameters, and it covers five scope selectors well, including the 'lat,lng' format, WGS84 GeoJSON, the 150 km² and 64-vertex limits, and the GSS code example. It says nothing about limit, radius_m, or the two min_*_headroom_mva filters, and it advertises an `lpa_code` scope that does not appear in the input schema at all.

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-level outcome and resource set: primary substations nearest-first with demand/generation headroom, voltage and distance, plus nearby REPD projects and operator data coverage. An agent can distinguish this from siblings like energy_profile or solar_potential without opening any 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?

Gives a hard usage rule — 'give exactly ONE scope' — with the full enumerated set of accepted scopes and the consequence of violating it ('refused before any read and nothing is charged'). It stops short of naming a sibling alternative for the cases it excludes (e.g. where to go for profiles or constraints), so it is clear context but not full when/when-not routing.

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