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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower, and the description still adds real context beyond them: the required scope (lots:read), the need for the caller's own Fonciq API key in the Authorization header, and the billing outcome ('returns no new document and is not billed (0 $)'). The only missing behavioral detail is what the response payload looks like when zero or multiple lots match.

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 English/first sentence is well front-loaded with the route and the core resolution semantics. However, the text is fully bilingual and duplicates every operational fact twice (billing, API key, 'not billed (0 $)' appear in both languages), so a meaningful share of the payload restates rather than adds information.

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 read-only, two-parameter lookup with no output schema, the description covers source, scope, auth, and cost, and it names the resolution outputs (lot number(s), cadastre, matricule). It falls short only on the mutually-exclusive-or-not question and on what happens when no lot matches, which an agent needs before calling.

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 both parameters are already documented in the schema, and the description only restates them as 'Give address or matricule'. It adds no semantics the schema lacks — no format examples for the matricule, no statement of whether address and matricule are mutually exclusive or may be combined. Baseline 3 applies.

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 states a specific verb+resource ('Resolves a Québec address or a property-assessment matricule to lot number(s), cadastre and matricule') and even names the backing route GET /v1/lots/resolve. That is far clearer than a tautology, but it never explicitly distinguishes itself from the sibling lot_get (retrieve a lot once you already have its number), leaving the resolve-vs-fetch boundary to inference.

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?

The instruction 'Give address or matricule' implies usage, and the source data ('from the municipal assessment rolls') hints at context, but there is no explicit when-to-use, no when-not, and no named alternative such as lot_get. Critically, both parameters are optional in the schema, yet the description never says what happens if neither, or both, are supplied — an ambiguity an agent will hit immediately.

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