route_between

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

With no annotations, the description must carry the full burden. It usefully discloses the 30-point cap and that distance/elevation are recomputed on a precise DEM (IGN in France, Copernicus elsewhere), which is genuine behavioral context. It omits whether the computed route is persisted or only returned, and gives no hint about cost or error behavior for unroutable points.

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-loads the core purpose in one sentence, then adds tightly scoped bullet notes on loop, difficulty, point limit, and elevation source. Little waste, though the loop bullet is slightly long relative to its value.

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?

An output schema exists, so return values need not be described. Still, with 0% schema coverage and no annotations, an agent lacks any explanation of the 'profile' enum or of whether the result is stored, and gets no sibling differentiation against the loop/route-search tools.

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%, so the description must compensate for all 5 parameters. It explains loop and max_sac_scale well (including the T1–T4 scale) and notes the 30-point waypoint limit, but leaves 'name' and the important 'profile' enum (hiking-mountain / hiking-beta / shortest) completely unexplained. Partial compensation only.

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+resource ('Calcule un tracé sur de vrais chemins passant par les points donnés, dans l'ordre') that clearly identifies route generation over real trail networks, respecting point order. It does not, however, distinguish itself from similar siblings such as generate_loop_candidates or find_hiking_routes, whose territory overlaps with the loop=True behavior described here.

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 via the loop semantics ('Pour une boucle via un lieu imposé (cascade, sommet), donner départ + lieu(x) avec loop=True'), which is a real when-to-use hint. But it never states when to prefer this tool over siblings like generate_loop_candidates, find_hiking_routes, or import_gpx, nor any prerequisites.

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