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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuine value beyond them: the data source ('Kranli, official publications'), the 90-day freshness ceiling, the newest-first ordering, and the exact fields each record carries (date, commune, official description, status, trades, official link, source, mandatory 'formule' notice). It does not mention rate limits or pagination, which keeps it from a 5.

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 purpose, source and ordering before any secondary detail, and every clause carries information. The full bilingual duplication roughly doubles the length, which is a format convention rather than padding, but it does cost some density.

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?

With no output schema, the description compensates by enumerating the returned fields and the sort order, which is exactly what an agent needs to decide whether to call it. Minor gaps remain: nothing about behavior when all filters are omitted, and nothing about how rayon_km widens results in practice or how results are capped.

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 description coverage is 100%, so the schema already documents every parameter, including the 90-day cap on jours and the 25 cap on limite. The description reinforces that commune/canton, metier and period are combinable filters, but it adds no syntax or interaction detail beyond the schema. Baseline 3 is appropriate.

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 with real scope: 'Search new building permit applications published in Switzerland ... official publications of the last 90 days', filtered by municipality, canton, trade and period, ordered newest first. That is far more informative than the bare tool name. It stops short of 5 because it never names what makes it different from lookup siblings like metiers or trouver_commune, leaving the routing inference to the agent.

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?

Usage is implied by the filter list ('by municipality or canton, trade and period'), so an agent can guess the intended context. But there is no explicit when-to-use, no statement of what to do first when the municipality or trade is unknown (resolve via trouver_commune / metiers), and no exclusion versus alternatives such as resume_semaine.

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