git_mutate

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

With no annotations, the description carries the full burden, and it does disclose meaningful traits: worktree must be verified, the call runs under project locks and is journaled, and it mutates git metadata (implying the operation is state-changing). However, it omits auth/permission requirements, reversibility or recovery after the journal, and failure behavior for an unverified worktree — significant gaps for a mutation tool.

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?

Two dense sentences, front-loaded with the action and scope, with no filler. It is jargon-heavy ('journaled', 'the mode's own git policy') but every clause carries weight.

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 journaled mutation tool with no annotations, no output schema, and 0% parameter coverage, the description covers behavioral framing but not the practical contract: what slug identifies, how args maps to the 'one subcommand', what path does, and what happens on failure. The agent has to guess at the call signature.

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 0% and four parameters exist, so the description must do the explaining. It only touches the branch default ('the workspace and branch default to the mode's own git policy'), leaving slug, args (the actual subcommand + argv), and path entirely undefined. Required parameters slug and args are the most consequential and get no semantic help at all.

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+resource ('Run one git subcommand in a verified worktree') and stakes out a clear scope claim ('the only path that writes a worktree's git metadata'), which separates it from siblings like git_root and verify_worktree. It stops short of naming those siblings explicitly, which is the only thing keeping it from a 5.

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?

Implies usage through the exclusivity claim — if you need to write git metadata, this is the only path — but never states when not to use it or which sibling handles read-only git inspection. A conditional hint ('the workspace and branch default to the mode's own git policy') gestures at routing but leaves the agent to infer alternatives.

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