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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. Beyond that, the description adds genuinely useful behavior: result ordering (distance if a location is given, otherwise alphabetical), what each result contains (reason for inclusion, nearest transport station, link to the record), and the hard cap of 50 on 'limite'. It stops short of saying what happens when nothing matches or how results are paginated.

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?

Dense and front-loaded: capability and scope come first, then ordering, then result contents, then the limit. No filler sentences, though the parenthetical product examples and the trailing 'limite' note are slightly compressed into one block.

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 an eight-parameter, filter-only read tool with no output schema, the description covers capability, location modes, ordering, result shape and the result-count cap — enough for an agent to call it correctly without further inspection. Only 'langue' and 'ouvert_samedi' remain unexplained, a minor gap against what is otherwise a self-sufficient definition.

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 0% and the schema exposes only bare titles, so the description carries the burden — and it does: it explains 'produit' (with examples), 'technique', the latitude/longitude pair, 'arrondissement', and the 50 maximum for 'limite'. Two of the eight parameters, 'langue' and 'ouvert_samedi', get no mention and their intent must be inferred from the French titles.

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 ('Imprimeurs parisiens capables de réaliser un produit ou une technique') plus the geographic scope (latitude/longitude or arrondissement), with concrete product examples. It does not, however, differentiate itself from the sibling 'rechercher_imprimeurs', which an agent could plausibly confuse with this tool.

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 parameter enumeration (give a product or technique, optionally a location or arrondissement) and the ordering rule tells the agent what output to expect. There is no explicit 'use this when…' statement, no prerequisites, and no routing to alternatives such as 'rechercher_imprimeurs', 'lister_techniques' or 'fiche_imprimeur'.

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