prepare_drive_speed_change

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

The annotations only declare the generic profile (readOnly=false, destructive=false, idempotent=false, openWorld=false), and the description adds genuinely non-obvious behavior: it reads and reports the session version, it leaves the speed untouched, zero speed holds rather than ends the session, values are clamped to the authorized speed/direction, and the returned setpoint is the quantized value following an internal ramp. That is substantive disclosure beyond the annotations. What remains unstated is whether a prepared change persists in session state and must be committed by a later call.

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?

The purpose is front-loaded in the first clause and the passage is short, with no filler sentences. However, the trailing clauses ('显示实际量化给定，沿用内部斜坡') are dense jargon whose meaning an agent must guess, and the compressed phrasing blurs preview behavior with return-value behavior.

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 explained, and the description does cover safety-relevant constraints (clamping, zero-speed hold, no speed mutation). For a staging/prepare operation that is not idempotent, it should still say what the prepared change is attached to, how the required speed argument is interpreted, and what job_id does.

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 0%, so the description carries the full burden, and it only partially compensates. It conveys one real semantic for the speed argument: zero is a legal value that holds the session, and inputs are clamped to the authorized speed/direction. It says nothing about the speed unit or sign convention, and the job_id parameter is never mentioned at all.

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 states a specific verb and resource: preview a speed change for the current background speed session, read the session version, and explicitly not modify the speed. That 'preview, not apply' framing lets an agent separate it from the sibling apply_drive_speed_change, although it never names that sibling outright.

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?

Usage is implied rather than stated: the word 'preview' plus 'does not modify speed' suggests calling this before a committing tool, but no alternative is named and no explicit when-not condition is given. The constraints that are stated (zero speed allowed to hold the session, respect the session's already-authorized speed/direction) are useful context but are not routing guidance.

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