Unstage Git Files

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

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true, and the description adds genuinely useful context beyond them: the mutation is confined to the index while working-tree content survives, the environment gate and its exact 403 `read_only` failure mode, and that git executes inside the app's running container and returns its output. It does not cover behavior for unstaged/nonexistent paths or permission scope, which keeps it off a 5.

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?

Three tight sentences, zero filler, with the primary effect front-loaded and the environment restriction and execution context following in priority order. Every clause adds information an agent needs before calling.

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 git mutation with five parameters, a nested request body, and no output schema, the description covers purpose, effect scope, the environment gate, and where git runs. Remaining gaps are minor: no auth/permission requirements and only a vague statement that its output is returned.

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%, so the description carries weight here, and it contributes real meaning for the `env` parameter by effectively narrowing the usable enum value to `development`. However workspaceSlug, appSlug, region, and the nested requestBody wrapper get no explanation at all, so the compensation is partial.

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?

Specific verb-and-resource: 'Take the given paths out of the index' names the exact git index operation, and 'their changes stay in the working tree' immediately separates it from discardGitChanges-style siblings where content would be lost. An agent can tell it apart from stageGitFiles and discardGitChanges without inspecting schemas.

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?

Gives a hard precondition ('Works only on a development app: any other app answers 403 read_only'), which functions as an explicit when-not rule and tells the agent what happens on misuse. It stops short of naming the sibling to use for staging or discarding, so it is clear context rather than full routing guidance.

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