package_manager

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

Without annotations, the description must fully disclose behaviors, but it fails to mention critical aspects: what happens if the package manager is missing, whether elevated privileges are needed, how output is returned (stdout vs exit code), or whether arguments are passed directly. The phrase 'with supplied arguments' lacks detail on execution context.

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 a single sentence, which is concise, but it omits essential information that would make it effective. While no words are wasted, the brevity sacrifices clarity and completeness, warranting a middle score.

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 simplicity (one parameter, no output schema, no annotations), the description should cover return values, error handling, and OS detection. It does not, leaving the agent underinformed. The tool's behavior in different OS environments or with invalid arguments is entirely unspecified.

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 0% description coverage for the 'args' parameter, and the description adds minimal meaning. It says 'with supplied arguments' but does not specify expected format (e.g., full install command vs individual tokens) or valid argument patterns. The agent must infer from the schema's array-of-strings type, which is insufficient.

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 the tool runs the native package manager (winget, brew, apt/dnf/pacman) with supplied arguments. It specifies exactly which tools are invoked and the generic nature of argument passing. No ambiguity with sibling tools exists as none are package manager related.

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 no guidance on when to use this tool versus alternatives like 'run_command' or 'spawn_process'. There is no mention of prerequisites, typical use cases (install, update, remove), or OS-dependency. The agent receives no help choosing this tool over others.

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