pi_terminate_agent

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

With no annotations, the description carries the full burden and does well: it discloses the mutation (task stopped), the state transition (marked interrupted), what is preserved (registered agent and context), and what is returned (partial latest reply). It omits idempotency, permission requirements, and whether a stopped agent can be resumed only via continuation.

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?

Two sentences with no filler; the action and its side effects come first, and the sibling-routing clause follows. Every clause 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?

No output schema or annotations exist, so the description must explain effects and returns; it does cover both, plus continuation semantics. The only material gap is the undocumented session_id parameter.

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% and the description never mentions session_id, so the single parameter's meaning is left entirely to the caller's inference. The name is suggestive but the definition adds no semantics beyond the schema.

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+resource ('Stop the current task') and enumerates the observable effects (marks it interrupted, returns partial latest reply). It explicitly contrasts itself with the sibling pi_release_agent, so an agent can pick between the two without reading either schema.

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?

Gives a clear when-not rule: use pi_release_agent to unload an idle runtime instead of terminating. It also states the continuation path (the agent/context is retained). No guidance is offered relative to pi_steer_agent or pi_followup_agent, but the primary discriminator is present.

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