cleanup_processes

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

Annotations already mark this as destructive, and the description adds important behavioral context: PID observations and old PID files do not authorize termination, attached targets detach, and the `terminated` count has a narrow meaning. It still leaves some ambiguity about what 'owned adapters and bridges' includes, but the key destructive boundaries are disclosed.

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 reasonably front-loaded and not bloated, but it repeats the force behavior in both the prose and the Args section. A little tightening would improve it, though nothing is seriously off-topic.

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 one-parameter, no-output-schema tool, the description covers what the tool does in both modes and adds caveats about termination authorization and counting. Return details for 'observation status' are not fully specified, but the critical operational context is present.

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 carry the parameter meaning. It does so: force=False shows status while force=True joins owner cleanup. This fully explains the practical effect of the single boolean parameter.

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 both modes clearly: viewing process observations and joining trusted-producer cleanup. It uses somewhat specialized terms ('observations', 'trusted-producer cleanup'), but the verb/resource distinction is still understandable and no sibling tool appears to overlap directly.

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 explicitly explains the two operating modes: without force it only reports status, and with force=True it performs owner cleanup. It does not name alternatives such as terminate_debug or runtime_smoke_stop, but the conditional usage is clear.

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