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

Beyond the annotations, it discloses that work runs asynchronously ('Returns a task'), that an external provider (TomTom or Azure Maps) performs the routing, the two failure modes ('No provider key returns ROUTING_NOT_CONFIGURED; past the monthly quota, PROVIDER_QUOTA_EXCEEDED'), and the replace-on-recalculate semantics of route_id. It also reinforces the non-destructive scope ('Creates no territory and changes no assignment'), which is consistent with destructiveHint=false and the mutation implied by readOnlyHint=false.

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?

It is front-loaded with the core action and return payload, and nearly every clause carries unique information rather than repeating schema or annotations. The cost is density: long semicolon-chained sentences jam route-type semantics, parameter rules, error codes and async behavior into one block with no structural separation.

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 12-parameter, nested-schema, open-world tool with an output schema, this covers the things the structured fields cannot: provider dependency, quota and key failure modes, async task return, recalculation semantics, and the isolation from territory/assignment state. Return values need not be explained because an output schema exists.

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%, so the description must carry the parameter burden, and it does for the hard cases: route_type's circuit/tour/open_tour modes, stop_sets ordering and the no-reordering-between-sets rule, point_id reference formats ('source.filter.territory_id', 'visits: <account_id>#<n>'), dwell_time, route_id, and map_session_id's drawing behavior. It leaves depart_at, ts_handle, route_label, travel_mode and include_geometry entirely undocumented, which keeps it short of full compensation.

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 verb and object ('Sequences and drives a set of stops') and enumerates the concrete outputs (order, road distance, drive time, per-leg timings, geometry, drawn map path). It also draws boundaries against siblings with 'Creates no territory and changes no assignment' and separates its drive-time measure from territory workload.

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?

It gives clear decision context: route_type is framed as a user choice with the three modes explained, and route_id is explained as either 'add a second route' or 'recalculate an existing route (e.g. to drop a stop)'. It also routes the agent toward analyze_routes for downstream dwell-time analysis. What's missing is an explicit statement of when NOT to use this tool versus a sibling such as schedule_visits or delete_route.

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