apply_drive_speed_change

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

Goes well beyond the annotations by disclosing that the running connection and heartbeat are reused, that version and motor parameters are re-verified before writing, and that the setpoint is read back. It also states two non-obvious failure semantics: a successful readback does not prove the drive actually reached the speed, and failures are not automatically retried. These are exactly the operational caveats annotations cannot 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?

A single dense sentence, but the primary action is front-loaded and each semicolon-delimited clause adds distinct information (priority, connection reuse, verification, readback caveat, no-retry). No filler, though the packed punctuation makes it slightly harder to scan than a short bulleted structure would.

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?

The output schema is present, so return values need no explanation, and the description covers safety-relevant behavior for a destructive, non-idempotent write. What is missing is the workflow context around plan_id — that a prepare step precedes this call — which an agent needs in order to invoke it successfully at all.

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 schema has one parameter, plan_id, with 0% description coverage, and the description never explains what a plan is, where plan_id comes from, or what its lifetime is. The clause about re-checking version and motor parameters hints that the plan carries that data, but the agent still has to infer the provenance of the only required argument.

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?

States a specific verb and resource: "执行用户要求的单次调速" makes clear this applies one speed change to the drive, and "单次" scopes it against continuous operations. It distinguishes itself from acquisition work ("优先于长采集") but never names the sibling prepare_drive_speed_change that produces the required plan_id, so the boundary with that tool is only implicit.

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?

Gives one concrete usage cue — this takes priority over long-running acquisition tasks — and the phrase "用户要求" implies it is invoked on explicit user intent. It does not state the precondition that a plan must already exist or point to prepare_drive_speed_change as the prerequisite step, which is the main routing decision an agent faces here.

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