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

Annotations already declare destructiveHint=true, but the description goes further by disclosing that cleanup is selective: artifacts edited since the run or still referenced elsewhere are preserved. It also reveals the dry-run-by-default behavior. It stops short of saying what a cancelled/partial undo returns.

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?

Two sentences, front-loaded with the destructive scope, then the retention caveat, then the preview switch. No 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 2-param destructive tool with no output schema and no annotation beyond hints, the description covers the essential risk and behavior. The only real absence is any indication of what the preview output looks like or how a runId is obtained.

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 0%, so the description must carry parameter meaning. It does explain `apply` semantics (preview unless true), but `runId` — the parameter that identifies which run's artifacts are removed — is never described, leaving half the surface to inference.

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 ('Removes') with an explicit resource set ('lanes, vehicles, cases and groups') and scopes it to artifacts written by a cs454_moving_loads run, which cleanly separates it from the sibling cs454_moving_loads and from generic undo tools like stages_undo.

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 implies use after a cs454_moving_loads run, but never states when to use it versus the many other *_undo siblings or what precondition (an existing runId) is required. Usage is inferable rather than stated.

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