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

Beyond readOnlyHint/destructiveHint it discloses matching methodology, the temporal and spatial windows, the exact output shape, an explicit limitations paragraph (nearest DPE may be a neighbouring building; medians unadjusted for location or sale year, so gaps are 'descriptive, not a measured green value'), and a cost of 10 credits. These are exactly the behavioral facts an agent cannot get from annotations and would otherwise mis-infer.

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 with the purpose, then methodology, then required/optional parameters, then output shape and limitations, then cost. The labeled sections make skimming easy and no sentence is filler — even the methodology detail is needed to interpret the result.

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 sketching the return object (classes with count, median, p25/p75, vs_median_pct, plus summary/methodology/limitations). Combined with the stated limitations, cost, and input granularity constraints, an agent has everything needed to decide to call it and to interpret the response honestly.

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 adds a constraint the schema does not encode: although the schema lists zero required parameters, one of code_postal or commune is genuinely required, and department-level input is explicitly rejected as too coarse. That is meaningful semantics beyond the schema; type_local's behavior is only lightly restated ('Maison|Appartement', default 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?

The description names a specific verb and resource ('price premium or discount of energy performance ratings') and then explains the exact mechanism: DPE diagnostics cross-referenced with DVF transactions within a 200m/10-year window. This is far more than a restatement of the title and makes the output concept ('median price/m² per energy class and its gap vs. the local median') unambiguous.

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 clear operating context by stating 'REQUIRED: code_postal or commune (department too broad for meaningful comparison)', which tells the agent the right granularity and implicitly rules out department-level queries. It does not, however, name a sibling tool (e.g. analyze_dpe_distribution) as the alternative for a rating-distribution-only question, so the routing guidance stops short of explicit when-not/alternatives.

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