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

Annotations already declare the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds material context beyond them: UK-only scope, a 30-credit cost, and the default band behaviour (E/F/G), all of which affect whether and how an agent should call it. Return format is not described, but an output schema exists.

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 the resource and ranking, then defaults, then targeting/usage guidance, then constraints (area id source, UK-only, cost). Short paragraphs with little waste; the clipped sentence fragments are compact rather than padded.

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?

Output schema exists, so return values need no explanation, and the description covers scope, cost, defaults, and the key parameter sources. The main gap is the unexplained limit parameter and the accepted bands values, which for a 0%-coverage schema is a minor but real omission.

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 0%, so the description is the only source of parameter meaning. It explains area_id (marts id from area_resolve), fuel (gas cohort), and bands (defaults to E/F/G), but leaves limit undocumented and doesn't state that bands accepts a list of A-G values. Solid coverage of the key params but not complete.

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 resource and scope ('properties in an area with the most improvement headroom, ranked by potential efficiency') and explicitly frames itself as a targeting/list tool, contrasting with the per-property siblings ('not a fact about one property'). An agent can distinguish it from property_energy_retrofit or energy_profile without opening a 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 clear use case ('combine with fuel=gas for the fossil-heated cohort') and frames the tool's role as generating an action list, which implicitly routes agents away from per-property tools. It stops short of naming an explicit alternative to use instead, so 4 rather than 5.

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