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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the tool is known to be safe and non-mutating. The description adds significant behavioral context: it states that public holidays and exceptional closures are taken into account, which is valuable beyond the schema. It also explains that the 'quand' parameter is in Brussels time, which is a behavioral nuance. However, it does not describe the output format despite having an output schema, and it doesn't mention any rate limits or errors. With annotations covering safety, a 3 is appropriate.

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 description is a single, dense sentence that front-loads the core purpose (agency in Dottignies) and then lists the key facts (address, map, phone, hours, open status, next opening, appointment rule, parking, access). It is concise, well-structured, and every clause contributes value. The exception about public holidays and closures is a useful highlight. No extraneous information is present.

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 information tool with only 2 optional parameters)Skip an output schema that provides return value structure, the description is remarkably complete. It covers all critical aspects: access points, temporal queries (with timezone), and special rules (appointment from 1 kg, holidays). Sibling-tool context shows this is one of many specialized tools, but the description gives enough detail for the agent to select it correctly without additional documentation. The annotation hints already cover safety, and the description fills in the domain-specific knowledge.

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?

The schema has 2 parameters with 50% coverage: 'langue' has an enum and is self-explanatory (fr/en/nl), but 'quand' is only described as 'Optional date-time to test, ISO 8601 local Brussels time'—the description adds key details: it is Brussels time, and it goes beyond a simple timestamp by specifying the purpose ('to test open status'). However, the description doesn't clarify the default behavior when 'quand' is omitted (presumably current time). Since schema coverage is moderate, the description adds moderate value, but not enough to fully compensate for the missing default behavior.

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 clearly states that the tool provides agency access information: address, map link, phone, opening hours, open status, appointment rule, parking, and access. The verb is implied ('get' or 'provide') but the resource is specific and well-defined. The title 'Agence : accès, horaires, ouvert maintenant' reinforces the purpose, but it doesn't explicitly differentiate from siblings, though siblings like 'preparer_visite' and 'coffres' are distinct in focus.

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 description implicitly tells the agent when to use this tool: whenever it needs agency details, opening hours, or open status. It mentions the optional 'quand' parameter for testing a specific date-time India time, which is a usage condition. However, there is no explicit exclusion like 'use preparer_visite for appointment pre-booking' or 'use cours_historique for historical rates.' The description is clear enough for typical use, but lacks explicit routing to alternatives.

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