git

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

No annotations are provided, so the description carries the full burden — and it does: the policy tiers, the hard refusals, pre-commit hooks always running, no glob expansion, submodule root resolution, and the cross-session HEAD-movement guard with its confirm:true override. It also explains expected_head as an optimistic-concurrency pin and what happens on mismatch ('refused before running'). This is unusually rich behavioral disclosure for a mutation-capable 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?

The purpose and the tier policy are front-loaded, then add/commit typing, then the guard, then the skill pointer — a sensible order with no wasted sentences. It is long, but the length is justified by the policy complexity; the only mild cost is that the tier list is re-enumerated between description and schema.

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 7-parameter, mutation-capable tool with no output schema, the description covers everything an agent needs to call it correctly: policy gates, refusal conditions, guard semantics, the override path, and a pointer to the skill holding the full tier table. Nothing material is left for the agent to infer.

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 the baseline is 3. The description's add/commit paragraph ('add stages with -A semantics; commit takes message, plus an optional files list for a path-limited commit') largely restates what the schema descriptions already say, including the 'args ignored for add/commit' rule. It adds little parameter meaning beyond the structured fields, so it lands at the baseline rather than above it.

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 opening states a specific verb and resource — 'Run git through one tiered, policy-gated tool (no shell, no agent-supplied command line)' — and immediately frames the tiering model. It also names what it is not (raw shell) and points to the narrower plumb-git skill, so an agent can distinguish it from run_command and the plumb family without opening the schema.

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 spelled out tier by tier: reads always run, writes need allow_writes (default on), destructive needs allow_destructive AND confirm:true, network needs allow_push AND confirm:true, and force-push to a protected branch or ad-hoc URL is always refused. It names the alternative to reach for ('the narrower plumb tool to prefer over a destructive git call: the plumb-git skill'), which is exactly the when-not/alternative guidance the rubric rewards.

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