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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds genuine context beyond them: it discloses the year-resolution fallback ('taken from the open roll when an address is given, or from annee') and clarifies output nature ('a list of what to verify, never a diagnosis').

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 trigger, then the risk inventory, then the resolution mechanics. It is dense but every clause carries information; the enumerated risk list is long but justifies its space as the tool's payload.

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 moderately complex tool with no output schema, the description conveys what is returned (risks, each with a year range and source) and how the year is resolved. It stops short of explaining municipalite's effect and return format details, but nothing critical to invoking it correctly is missing.

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 only 20%, so the description must compensate, and it does for the load-bearing params: it explains how adresse and annee interact for resolving the year, and province is required. The roles of municipalite and lang are not spelled out in the description, leaving a small gap.

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 and resource: it lists risks documented by official sources for a home's construction era, with named examples. It is unmistakably distinct from the finance/inspection siblings (frais, taxe, taux, stats), so an agent can route to it 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?

Explicit trigger conditions are given: 'when someone asks what to check in a house given its age, or before an inspection.' No sibling alternatives are named, but the use context is clear enough for confident selection.

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