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

Beyond the annotations (readOnlyHint, destructiveHint=false, openWorldHint=false, which already establish a safe read), it discloses the return shape (count, distribution, pct) and a concrete credit cost of 10 — the latter is genuinely useful budget information not available in structured fields. It also states the location constraint, although that constraint is unenforced by the schema, leaving a mild ambiguity about what happens if no location parameter is supplied.

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 purpose sentence is front-loaded, and the REQUIRED/OPTIONAL/Example/Cost block structure makes it scannable. Every element earns its place, though the example and field listing slightly overlap with what the schema already documents.

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?

There is no output schema, and the description compensates by documenting the returned fields and percentages, plus cost. Combined with the fully described 5-parameter schema and safety annotations, an agent has everything needed to call it correctly; the only soft spot is the mismatch between the stated location requirement and an empty required list.

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; the description goes further by imposing a cross-parameter rule ('at least one location') that the schema itself does not encode (required is empty). The worked example ('code_postal: "75011" → { count: 42300, ... }') also ties a parameter value to a concrete output, adding interpretive value.

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 opens with a specific verb and resource ('Get the DPE (energy performance) class distribution for a location') and immediately names the unit of analysis (A–G ratings across diagnosed properties). This is clearly distinct from siblings such as analyze_dpe_price_and_thermal_risk or analyze_dpe_price_premium, which address price/thermal questions rather than raw rating counts.

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 explicitly states the input requirement ('at least one location — code_postal, commune, or code_departement') and lists optional narrowing filters (type_batiment, date_debut), which tells the agent how to scope a call. It does not, however, say when to prefer this over sibling DPE analyses, so there is no explicit alternative routing.

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