Cherry Pick Git Commit

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered; the description adds substantive behavior beyond that: failure atomicity ("if the cherry-pick fails, it is aborted and the call fails"), an environment gate returning 403 `read_only`, concurrency refusal, and the fact that it runs git inside the app's container and returns its output.

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?

Four short sentences, each carrying distinct information: the action, the concurrency precondition, the failure semantics, the environment restriction, and the return behavior. Nothing is repeated from the annotations and there is no filler.

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 destructive, no-output-schema mutation, the description covers what matters operationally: preconditions, failure/rollback behavior, permission gate, and what is returned (git output). The remaining gap is parameter-level, particularly how env and region should be supplied, which the schema does not document either.

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 only 20% across five parameters (including a nested requestBody), so the description is expected to compensate, and it largely does not. It never names the sha, workspaceSlug, appSlug, or region parameters; the only indirect signal is the development-app restriction, which touches the `env` enum without clarifying how env interacts with 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?

"Apply the given commit to the current branch as a new commit" gives a specific verb, resource, and outcome, and is immediately distinguishable from siblings like revertGitCommit, mergeGitBranch, or rebaseGitBranch. An agent can tell what this does 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?

It states two concrete preconditions that select against invocation: refusal while another merge, rebase, revert, or cherry-pick is in progress, and the requirement that the app be a development app. It does not explicitly name the sibling alternatives (revertGitCommit, mergeGitBranch) the way a 5 would, but the when-not conditions are unusually explicit.

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