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

Annotations already establish the safe read-only profile (readOnlyHint=true, destructiveHint=false). The description adds meaningful context beyond that: it discloses the subscription-key auth requirement, describes what results contain (geometry or travel costs plus source metadata), and states that unroutable requests fail with an error requiring revised inputs. This is useful operational disclosure the annotations do not carry.

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-loaded with the operation list, then capacity limits, then auth and error behavior in three compact sentences. Every clause carries information and nothing is padded, though the dense run-on listing without formatting slightly reduces scannability.

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 six-operation tool with no output schema, the description covers operation inventory, per-operation size limits, auth, error handling, and a summary of return content. The main remaining gap is the unresolved overlap with the sibling `route` and `isochrone` tools, which an agent must be told how to disambiguate.

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 100%, so the baseline is 3, but the description genuinely adds constraints absent from the schema: the 2-10 route waypoint range, the 3-20 optimize stop range, the 625-pair matrix cap, and the 1,000-point map_match trace limit. It also clarifies that elevation is optional for route, tying the boolean parameter to a concrete 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 opens with a specific resource and enumerates all six operations (route, matrix, isochrone, map_match, snap, optimize), so an agent knows exactly what capability is behind the name. However, it never differentiates from the sibling tools `route`, `isochrone`, and `elevation`, whose names overlap directly with operations and parameters this tool exposes, leaving genuine ambiguity about which tool to pick.

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?

Per-operation constraints (2-10 waypoints, 625 pairs, 1,000 trace points, 3-20 stops) implicitly guide which operation suits a given workload, and the schema supplies per-operation parameter notes. But there is no explicit when-to-use-this-vs-`route`/`isochrone` guidance and no stated exclusions, so selection against siblings is left to inference.

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