Prune

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

Annotations only tell the agent this is a non-readOnly, non-idempotent mutation; the description adds no behavioral context whatsoever — it never says what gets pruned, that branches may be deleted, or that pruning is irreversible. The closing claim about resets not disturbing in-flight work is a generic subsystem property, not a disclosure about this tool's effects. It does not, however, contradict the annotations.

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 text is reasonably short and front-loaded, but the entire body is concept boilerplate that is not specific to pruning, so most of it does not earn its place for the purpose of invoking this tool.

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 12-parameter mutation tool with no required parameters, mode-dependent behavior, and a destructive prune_merged option, the description omits the operation semantics entirely. The presence of an output schema excuses explaining return values, but not the missing account of what prune does and when.

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% and all 12 parameters (including mode-specific ones like prune_merged, stale_days, force, adopt) are documented in the schema itself, so the baseline of 3 applies. The description contributes nothing beyond the schema — it does not clarify which parameter set corresponds to a prune invocation.

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?

"Prune (rm_worktree)" merely restates the tool name and title, and the remaining sentences describe the worktree subsystem in general (shared .git, branch layout, canonical checkout) rather than what this tool actually does. Nothing distinguishes it from siblings like rm_worktree_audit, rm_worktree_remove, or repository_manager_worktree_hygiene, and the fact that prune deletes merged worktrees and admin pointers (per the schema's prune_merged param) is never stated.

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 guidance, no prerequisites, and no named alternatives despite a dense family of worktree tools (rm_worktree_audit, rm_worktree_remove, rm_worktree_hygiene, rm_worktree_list). The generic architecture blurb implies a worktree context but never tells the agent when prune is the right call versus those siblings.

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