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

Annotations already declare destructiveHint=true and non-idempotent, and the description adds real context beyond them: async execution, the returned status/queue_id, and the dedupe behavior for in-flight jobs. It stops short of saying what the reordering actually changes on the route or whether it can be undone, which is the main thing an agent weighing a destructive write would want.

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?

Four short sentences, front-loaded with the WRITE marker and the core action, then prerequisites, then async contract. No filler and nothing buried.

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 destructive async mutation with no output schema, the description supplies the missing pieces: prerequisites, that the call returns immediately with pending/queue_id, how to poll, and the duplicate-job behavior. An agent can invoke and follow up correctly from this alone.

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 100%, so route_id and timezone are already documented in the schema. The description adds no parameter-level detail, not even a note about when timezone matters, so the baseline of 3 applies.

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?

Opens with a specific verb and resource ("start optimizing a route's stop order") and prefixes WRITE to flag the mutation class. The async/polling follow-up immediately separates it from upper_get_optimization_status and upper_assign_drivers.

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?

States the explicit preconditions (at least one stop and one assigned driver, pointing to upper_assign_drivers) and the next step (poll upper_get_optimization_status). It also covers the edge case where a job is already running, so an agent knows the expected response instead of double-submitting.

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