Merge

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false, so the safety profile is largely covered by structured data. The description adds the worktree model (shared .git, no re-clone, canonical checkout stays on the default branch), which is useful environmental context. However, it says nothing about merge-specific behavior such as conflict handling or what state the branch is left in after the merge.

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 opening line duplicates the name and title, and the bulk of the text is a general worktree concept primer that is tangential to the merge operation. It is reasonably front-loaded and not bloated, but a significant share of the text is not earning its place relative to the tool's actual job.

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?

This is a 12-parameter tool whose schema references many distinct operations (add, remove, audit, sync, list, bulk_add, merge) with no action discriminator, yet the description never clarifies which operation this tool performs or how its parameters map to it. An output schema exists, so return values need not be explained, but the invocation-side completeness for such a complex surface is inadequate.

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 each of the 12 parameters (base, into, strategy, etc.) is already documented in the schema, including the operation-specific notes like "strategy: 'rebase' or 'merge'". The description adds no parameter-level meaning beyond that, so the baseline of 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?

The description opens by restating the name/title ('Merge (rm_worktree)') and then spends its whole length explaining the general worktree concept rather than what the merge operation itself does (merge which branch into what, and when the operation is warranted). An agent cannot tell from this text how rm_worktree_merge differs from rm_worktree_sync, rm_worktree_reset_branch, or the rm_merge_queue_* siblings. It is background orientation, not a statement of purpose.

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?

There is no when-to-use or when-not-to-use guidance, and no named alternative among the many overlapping siblings (sync, reset_branch, merge queue). The description never indicates the conditions under which a merge is the right call versus a rebase/sync or a queued merge. No explicit context is provided.

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