uvcs_undo_prepare

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

The description does add valuable context beyond the schema (irreversibility, root-path prohibition, token return), which is normally creditable. However, it claims this call irreversibly undoes changes while annotations declare readOnlyHint=true and destructiveHint=false; the description's framing makes the tool look destructive when the prepare step is not, creating a direct conflict with the structured safety signals.

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?

Four short sentences, each carrying a distinct fact (action, scope restriction, workflow requirement, return value). The destructive consequence is front-loaded, which is exactly right for a high-risk operation.

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?

With no output schema, the description should clarify the token's use and lifetime and that uvcs_undo_confirm performs the actual undo; it only says "short-lived confirmation token." The core risk facts are present, but the handoff to the confirm step and the token contract remain underspecified for a destructive workflow.

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 100%, so both itemPath and recursive are already fully documented in the schema. The description's "one path" and "workspace-root undo is forbidden" restate the schema's itemPath constraint without adding syntax, format, or recursive-handling detail, so baseline 3 applies.

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 ("undo pending changes") plus the scope restriction ("for one path inside the selected workspace"). It signals the prepare/confirm pairing, though it never names the sibling uvcs_undo_confirm by name, so the agent must infer which tool completes the operation.

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?

"Workspace-root undo is forbidden" and "Requires prepare/confirm" give real invocation constraints, but the description never says when to choose undo over alternatives such as uvcs_revision_diff or uvcs_checkout, nor what to do with the token afterwards. Usage is implied rather than spelled out.

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