kill_agent

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

No annotations are provided, so the description carries the full burden. It does disclose the key destructive traits — 'force-terminate' and 'immediately' — but omits permissions, effects on the session, and irreversibility.

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?

One front-loaded sentence with no wasted words; the 'Legacy helper' prefix flags context efficiently. However, its brevity leaves important gaps unaddressed.

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, unannotated tool with an undocumented parameter, the description is too thin. Output schema coverage helps for return values, but missing usage and parameter detail leaves the agent under-informed.

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 single parameter session_id has 0% schema description coverage and the description never mentions it. The phrase 'a session's subprocess' only loosely implies it, adding no real semantics.

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?

States a specific verb ('force-terminate') and resource ('a session's subprocess') and adds scope ('immediately'). It does not explicitly distinguish itself from sibling cancel_run, though 'force' and 'legacy' hint at a difference.

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?

Offers only the label 'Legacy helper' as usage context; it never says when to choose this over cancel_run or other siblings, nor any prerequisites. An agent must infer that it is for immediate forced termination.

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