Défibrillateurs à La Réunion

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

Annotations already cover read-only/idempotent/open-world, so the description's added value is the result content (distance, walking time, exact placement, 24/7 vs opening hours) and the safety prompt to call 15/112. Coverage figures (1,200 devices across 24 communes) help the agent judge whether empty results are plausible, though pagination/result limits remain unstated.

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 core purpose, data source and returned fields are front-loaded in the first sentence, with examples and the emergency-number reminder following logically. Slightly dense and the bilingual one-line tail is redundant for a francophone consumer but harmless.

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 does the necessary work of enumerating what a result contains and how proximity is expressed, plus the empty-input behavior (which the schema also covers). Missing only result-count/pagination expectations, which is minor for a lookup tool.

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% and the single 'lieu' parameter is already documented in detail (commune, beach, quartier, cirque, summit, 'lat, lon', empty = whole island). The description's examples reinforce that but add no syntax or format detail beyond the schema, so the 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?

States a specific resource (nearest AEDs/defibrillators), a specific geography (Réunion, 974), a named data source (base nationale Géo'DAE), and the fields returned (address, distance, walking time, exact location, access hours). No sibling tool overlaps, so differentiation is implicit but 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?

The 'Pour :' examples clearly indicate the intended query shape (nearest AED to a beach, AED in a cirque), which tells an agent when to reach for it. It stops short of stating exclusions or alternative tools, but the sibling list contains no competing emergency-equipment tool.

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