run_process

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

No annotations are provided, and the description fails to disclose critical behavioral traits such as security implications (e.g., running arbitrary programs), potential for system impact, or need for permissions. This is a serious gap for a tool that executes processes.

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 brief and uses bullet points for parameters, making it scannable. However, the first line is slightly redundant with the tool's name, and the format could be tightened slightly.

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 tool's nature (executing programs on a host), the description is insufficient. It lacks details on return values (despite an output schema), error handling, timeouts, or security contexts. The simplicity of the tool is not matched by adequate completeness for safe use.

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?

With 0% schema description coverage, the description compensates well by explaining each parameter's CLI flag and providing an example for 'args'. The meanings of 'suspend', 'with_output', and 'impersonate' are clarified beyond their schema titles.

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 verb ('Run') and resource ('program on the agent host'), using a specific invocation ('ps run'). It distinguishes itself from siblings like execute_shell, execute_raw, bof_process by implying it's for running arbitrary executables with arguments.

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?

No guidance on when to use this tool versus alternatives (e.g., execute_shell for command execution). There is no mention of prerequisites, limitations, or when not to use it, leaving the agent without context for selection.

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