cancel

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

With no annotations, the description carries the full burden, and it does disclose the important two-phase escalation: try to interrupt, otherwise terminate the CLI. However, it omits whether this is irreversible, what happens to in-flight work or session state, whether the session_handle becomes invalid, and whether there is any confirmation step — all critical for a terminating operation.

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?

A single tight sentence with the action front-loaded and no wasted words. It is efficient, though the brevity borders on under-specification for a destructive tool rather than being genuinely complete.

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 terminal, non-read-only operation with zero annotation coverage, no output schema, and an undocumented required parameter, the description should say more about irreversibility and post-conditions. As written, an agent cannot fully predict the consequences of invoking it.

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?

Only 50% schema coverage and the description adds nothing about parameters. The required session_handle has no description anywhere, so an agent has no guidance on its format or how to obtain it; only workspace_path is documented, and that documentation comes from the schema, not the description.

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 and resource: stop the running turn, with the added detail that it escalates to ending the CLI. This distinguishes it from the sibling read-oriented tools (doctor, consult, review, session, issue), though it never explicitly contrasts with them.

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 explains the mechanism (interrupt then kill) but gives no guidance on when to call it versus alternatives, no preconditions, and no note on when it should not be used. An agent must infer that this is the abort path.

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