worktree_apply

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

With destructiveHint=true already declared, the description adds real value: it names the consent precondition, states the default is a non-mutating plan, and bounds the blast radius ('Never removes worktrees or user files'). It stops short of describing exactly what files/config it writes when confirmed, but the safety envelope is well disclosed.

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 purpose and immediately followed by the consent/confirm gate and the scope guarantee. 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 5-param, 0-required mutation tool with no output schema, it covers the essential agent questions: consent, default behavior, and scope of destruction. It omits partial-failure behavior and how item vs all_safe selection interacts, but nothing critical is missing.

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%, so item, confirm, json, all_safe and workspace_path are all documented in the schema itself. The description reinforces confirm's plan-vs-mutate semantics but adds no new syntax or format detail beyond the schema, 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 (Apply) and resource (selected audit recommendation items) and enumerates the item kinds it handles (policy/hook/seed/tool-prune). This clearly distinguishes it from the audit-producing sibling worktree_audit and from read-only siblings like worktree_status.

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?

It says when the mutation actually happens ('Requires confirm=true to mutate; without it returns the plan'), which tells the agent to call it in dry-run first. It does not point at an explicit alternative tool for inspecting recommendations, so it stops short of full when/when-not routing.

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