apply_merge

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

The description discloses important non-obvious behavior beyond the annotations: finalize:true writes the merge checkpoint, reloads the editor, waits for reconnect, and returns vcs_status, while finalize:false does not reload. This is meaningful contextual information that the annotations alone do not provide, and it does not contradict them.

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 description is compact and well structured: one summary sentence, the two-call protocol, the side-effect/reload warning, and the explicit when-not-to-use alternative. Every sentence earns its place and the most important constraints are front-loaded.

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 description covers the required call sequence, the side effects of finalize:true, and the abort alternative. It is slightly incomplete in that it does not describe the return behavior or resulting state of the finalize:false pass, but given the small parameter surface and the rich two-phase guidance, this is a minor gap.

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 already 100% for both parameters, so the description does not need to restate them. It adds value by clarifying the behavioral difference between finalize:false and finalize:true and by referencing where mergeId originates ('from start_merge'). Minor extra detail about mergeId format would be nice, but the existing schema plus description is sufficient.

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 ('apply'), a clear resource ('a merge'), and a precondition ('whose conflicts are all resolved'). It also separates this tool from the broader merge workflow by naming cancel_merge as the abort alternative, so an agent can identify what apply_merge does without ambiguity.

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 made explicit: 'Call twice: first with finalize:false to prepare and review, then finalize:true to commit.' It also provides a direct exclusion with an alternative tool: 'When NOT to use: to abort a merge (use cancel_merge).' This gives clear, actionable guidance with no inference required.

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