run_git

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

No annotations are provided, so the description carries the burden. It discloses that it returns stdout and requires git on PATH, but it does not mention side effects of mutating commands (e.g., commit, push), stderr handling, or exit codes. For a tool that can execute arbitrary git commands, this is a notable gap, but the basic behavior is stated.

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 two sentences, front-loaded with the core purpose, and the example list is useful without being verbose. Every sentence adds value.

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 simple two-parameter tool, the description is mostly sufficient: it explains what it does, gives examples, and notes the path requirement. However, it lacks warnings about side effects and error behavior, which would be expected given no annotations. Still, the schema covers parameter details, and the tool's scope is clear.

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% with clear descriptions for command and cwd. The tool description lists example command values (status, diff, etc.) which adds slight context, but mostly repeats what the schema already conveys. Hence baseline 3.

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 clearly states 'Executes a git command and returns stdout' with a specific verb and resource. The list of example subcommands (status, diff, log, add, commit, branch, push) makes the scope unambiguous and distinguishes it from siblings like run_bash and run_adb.

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 concrete use cases (git status, diff, log, add, commit, branch, push, etc.) and states a prerequisite (requires git on PATH). However, it does not explicitly say when not to use it (e.g., for non-git commands) or mention alternatives like run_bash for non-git shell operations.

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