uvcs_merge_prepare

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

The description describes a state-changing merge whose result 'stays pending until a checkin', which is a workspace mutation, yet annotations declare readOnlyHint=true. That is a direct safety-profile contradiction. The useful details about refusals and the short-lived token cannot offset the contradictory read-only claim.

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?

Three tight sentences, front-loaded with the action and immediately followed by the refusal conditions and the mutation lifecycle. No filler, and each sentence contributes a distinct fact.

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?

No output schema exists, and the description does disclose the return value (a short-lived confirmation token), plus preconditions and the pending-until-checkin lifecycle. It is almost complete, but the ambiguity it creates about whether prepare itself writes to the workspace undercuts the safety picture.

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 100%, and the schema already documents both parameters with concrete examples (/main/task, cs:94, lb:LABEL). The description adds no parameter-level meaning beyond that, so the 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?

Specific verb (merge) plus precise resource set (branch/changeset/label) and destination (current workspace branch), which plainly distinguishes it from uvcs_merge_preview (dry run) and uvcs_merge_confirm (completion).

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?

Explicit preconditions: refuses while tracked pending changes exist, refuses on conflicts (resolve in the UVCS client), and requires the prepare/confirm flow. It gives clear when-to-use context and when-not, but does not explicitly name uvcs_merge_preview as the recommended prior step.

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