execute_drive_position_move

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

The annotations already state destructive=true, openWorldHint=true, non-idempotent, and not read-only; the description then adds substantive detail about behavior: the execution happens in the background, re-checks coordinates/feedback/config, maintains a heartbeat, verifies the target position, performs an OFF1 stop and release, and restores settings. What remains unstated is what happens when verification fails or the heartbeat is lost. Even so, the added process detail is meaningful beyond the annotations.

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 a single dense sentence with no filler words; the precondition that the user allowed the change is correctly placed first. However, the semicolon-chained clauses (re-check, heartbeat, verify, OFF1 stop, restore) form a run-on that is hard to scan, and there is no separation of preconditions and effects.

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?

An output schema exists, so return values need not be described, and the annotations already cover the safety profile. The description still omits key operational facts: what plan_id refers to, which runtime status and stop tools are meant, and how aborting or failure interacts with the temporary configuration.

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?

The single required parameter, plan_id, has 0% schema-description coverage, and the description never mentions it or explains where it comes from. The phrase '预览中的位移' only weakly implies that the ID originates from a prior preview/plan step. With such low schema coverage, the description should carry the burden, but it does not.

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 uses a specific verb and resource ('执行一次后台定位' = execute a background positioning move), and it clearly distinguishes this tool from the preview/planning step ('用户允许预览中的位移及临时配置后'). A reader can tell that this tool actually executes a previously previewed position move, while the planner only previews one, even though the description does not name that sibling tool explicitly.

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?

The description states the precondition clearly: the user must have allowed the position move and temporary configuration during preview. It also says to use the existing runtime-status and stop tools to query or abort, which points to the right alternatives for those actions. However, it never names those siblings, and it does not explain the failure path, so it remains at 4 rather than 5.

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