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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds value the annotations do not: the external routing engine (OSRM) is named, and the result structure "per leg and in total" is disclosed, which matters because there is no output schema. It omits limits (max 25 stops), error modes, and rate/usage expectations for the external service.

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, both front-loaded: what the tool computes and returns first, the calling convention second. No filler, no restatement of the title.

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 only 2 parameters, no output schema, and strong annotation coverage, the description does enough: it explains the return shape and the waypoint source. The gaps are the unmentioned mode parameter and the stop-count limit, which an agent would only find by reading the schema.

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 50% – the mode enum is self-documenting in-schema, but waypoints carries no per-field descriptions. The description partially compensates by implying order sensitivity ("in order") and by pointing to parse_map_link for the waypoint shape. It never mentions mode, the 2–25 item bounds, or lat/lng semantics, so the description adds only partial meaning over the schema.

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 first sentence names a specific computation (distance and travel time), the resource (a route through ordered stops), and the granularity of return (per leg and in total). It also names the upstream sibling parse_map_link, so an agent can place it in the workflow. It does not explicitly contrast with export_waypoints, so it stops short of full sibling differentiation.

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?

"Pass the waypoints from parse_map_link" gives a concrete precondition that ties this tool to one specific caller, which is real routing guidance. It is silent on when NOT to use it (e.g. single-waypoint cases that geocode would serve, or exporting via export_waypoints), so there are no stated alternatives or exclusions.

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