Calcule un itinéraire routier complet entre une origine et une destination (voiture, France, OpenStreetMap) : distance, durée, étapes de navigation en français, boîte englobante et géométrie encodée. Plan minimum : Business. Mention OSM ODbL obligatoire. Pour de simples distances en masse, préfère route_matrix.
| Name | Required | Description | Default |
|---|---|---|---|
| origin | Yes | ||
| destination | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses key behaviors: uses OSM data (requires ODbL mention), requires Business plan, and returns specific output components. Lacks details on read-only nature, rate limits, or error handling, but the essential safety and attribution info is present.
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?
Two sentences: first packs core functionality and output, second gives alternative usage. No filler, information density is high, and key points are front-loaded.
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?
Covers main inputs (origin/destination), outputs, plan, and attribution, but omits input format details (partial coordinates, XOR requirement) and any response structure. With no output schema and no annotations, the description should be more explicit about input constraints.
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 0%, yet the description only mentions 'origine' and 'destination' generically, failing to explain the lat/lon/address structure or XOR constraint. The schema itself provides some hints (min/max for lat, minLength for address), but the description adds no value beyond naming the parameters.
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 the tool computes a complete road route (car, France, OpenStreetMap) and lists output components (distance, duration, steps, bounding box, geometry). It distinguishes from sibling route_matrix by directing simple bulk distances to the latter.
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?
Explicit guidance: 'Pour de simples distances en masse, préfère route_matrix' provides a when-not-to-use and alternative. Also specifies plan minimum (Business) and OSM attribution requirement, setting clear usage constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct operation: search, verify, nearby lookup, company details, routing, matrix, etc. The descriptions explicitly cross-reference similar tools (e.g., 'préfère route_matrix' for bulk distances, 'préfère verify_address' for confirmation), making the boundaries clear.
Most tools follow a consistent verb_noun pattern (search_address, get_company_details, verify_address). The exception is 'route_matrix', which is a noun phrase and breaks the pattern, though it remains readable and predictable enough.
With 9 tools, the set is well-scoped within the ideal range. Each tool provides a meaningful capability without overlap or redundancy, covering address, company, routing, and locality data.
The server covers the core read-only workflows for its domain: address search/verification/nearby, company search/details, route calculation/matrix, and locality search/list. No obvious gaps or dead ends exist for a data lookup service.