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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds real context: no extra fee, a hard 15-minute time limit, the state transition to ASSIGNING_DRIVER with a new driver search, and the underlying DELETE endpoint. This goes materially beyond what the annotations convey.

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?

Three tight sentences, front-loaded with the WRITE marker, then constraint, then prerequisite. Every clause carries operational information; nothing is filler.

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 mutation with no output schema, the description supplies the timing constraint, prerequisite lookup, state outcome, and cost impact. The confirm gate and reason enum live in the schema, so nothing an agent needs is missing.

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 adds provenance for driver_id by pointing to lalamove_get_order for the current driver id. It does not explain reason or the confirm gate, which the schema already handles in detail.

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 an explicit verb and resource ("ask Lalamove to replace the driver of an order") and tags it as a WRITE operation. That is clearly distinct from siblings such as lalamove_get_driver, lalamove_cancel_order, and lalamove_track_order, so no schema comparison is needed to identify it.

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?

Spells out the exact eligibility window (15 minutes after driver match, before pickup) and the prerequisite data source ("Needs the current driver id from lalamove_get_order"). It also names the outcome (back to ASSIGNING_DRIVER), which tells the agent when this is the right tool rather than cancel or track.

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