Run Git Action

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

The description adds the important behavioral note that commits reside in the container and vanish unless pushed, which is beyond the destructiveHint annotation. It also implies mutating operations via the listed actions, but does not elaborate on all side effects (e.g., discard intentionally removes changes).

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 extremely concise and front-loads the list of actions in a single sentence. It avoids redundant wording and efficiently conveys the core behavior and the critical caveat about commit persistence.

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 complex nested oneOf schema with action-specific requirements, the description is far too terse. It does not explain which parameters are needed for each action, nor does it address the destructive nature of certain operations (e.g., discard, revert). The agent would need to deeply inspect the schema to use the tool correctly, and the description provides negligible context to aid that process.

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 schema has only 20% description coverage (only requestBody is described). The tool description lists valid action values but does not explain the required workspaceSlug, appSlug, env, or region parameters, nor how the requestBody varies per action. This leaves too much for the agent to infer from the schema alone.

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 explicitly lists all supported actions (discard, stage, unstage, commit, checkout, merge, rebase, revert, cherry, pull, push), making its purpose unmistakable. It clearly distinguishes from sibling read-only tools like getGitDiff or getGitOverview by focusing on mutating git state.

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 some guidance (e.g., 'One action per call' and the ephemeral nature of commits) but does not explicitly state when to use this tool versus alternatives. It lacks explicit contrasts with sibling tools like inspectSource or getGitDiff, leaving users to infer the intended use case from the action list.

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