build.install_dependencies

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

With no annotations provided, the embedded flags approval required, workspace write, network, and risk dangerous carry the behavioral disclosure burden, and they clearly warn that this is a side-effecting operation that needs approval and network access. The description does not detail which files are modified, but the workspace-write and dangerous flags convey the essential risk profile. No contradiction with annotations exists because there are no annotations.

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 one compact sentence with high-signal risk flags in front, followed by a clear purpose. There is no redundant explanation or filler; every part earns its place.

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 tool with one optional parameter and no output schema, the description covers purpose and safety but leaves workflow details unstated, such as what happens if no project is detected or how this integrates with build.detect_project. The core calling decision is mostly supported by the schema enum, but the operational context around detection and side effects is incomplete.

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 0%, so the description must compensate for the undocumented kind parameter. The phrase specified mobile project type hints at how to influence the parameter and detected suggests behavior when it is omitted, but it never names kind or lists the enum values. The schema enum supplies the valid values, but the description adds only partial semantic context.

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 states a clear action and object: install dependencies for a mobile project type. It does not explicitly name sibling tools, but the dependency-installation purpose is distinct from ios.install_app and build.run_lint. The phrase detected or specified adds some scope without listing the supported project types.

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 implies this tool is used after a project type is detected or when the caller specifies one, which gives a weak usage condition. It does not name when to prefer this over sibling build tools or state exclusions, so the guidance is implied rather than explicit.

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