git-reset

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It fails to mention that a hard reset destroys uncommitted changes, that this is a destructive operation, or any permissions or prerequisites (e.g., clean working tree). The agent may not understand the consequences of using this 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 description is a single concise sentence with no filler words. It is front-loaded with the core purpose. However, it could be slightly more structured (e.g., listing behaviors) without hurting conciseness.

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?

Given the tool's complexity (3 parameters, no output schema, potentially destructive), the description is insufficient. It does not explain return values, failure modes, or prerequisites like a clean working tree for hard resets. The agent lacks critical context to invoke the tool safely.

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?

The input schema covers 100% of parameters with descriptions (mode enum, target, directory). The tool description adds no additional meaning; it only reiterates that the tool resets to a commit/state. Since schema coverage is high, a baseline score of 3 is appropriate.

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 'Resets repository to a specific commit or state' clearly states the action (reset) and the resource (repository/commit/state). It distinguishes from siblings like git-checkout (which moves HEAD but not index/working tree) and git-rebase (which rewrites history) through the specific verb 'reset', but does not explicitly contrast with them.

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?

The description provides no guidance on when to use this tool versus alternatives like git-checkout, git-revert, or git-cherry-pick. It also does not explain the different reset modes (soft, mixed, hard) and their appropriate use cases, which is critical for an AI agent to select the correct tool.

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