Interrupt work in an existing T3 thread

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

The description goes well beyond the annotations by disclosing stale observation rejection, the lack of atomic turn targeting due to session-based interrupts, and the fact that the action does not archive or delete the thread. It also tells the agent how to confirm the result.

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?

Four sentences cover purpose, prerequisite, failure behavior, guarantee caveat, and confirmation step without filler. The essential instruction is front-loaded and every sentence adds value.

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?

With an output schema available)Skip? Need complete. Let's finish.The description covers prerequisites, stale rejection, atomicity limitations, non-destructive scope, and confirmation method. An agent has enough context to decide whether to call this tool and how to invoke it correctly. The only small gap is semantic detail for idempotencyKey, but the overall definition is highly complete for this operation type.Need final answer JSON. Need avoid cutting off. Let's produce final complete JSON. But before final, let's revisit all dimensions and ensure robust justification. We can include full

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 for expectedTurnId by tying it to 'latestTurn.turnId' from a prior thread read. threadId is reasonably inferable from the name, but idempotencyKey is left with only its name and schema constraints.

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 a specific action on a specific resource: 'Request stopping the active turn in a thread.' It adds scope by covering turns 'started outside this gateway' and explicitly disambiguates from archive/delete behavior, so an agent can distinguish it from closely related sibling tools.

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 gives a clear precondition and procedure: 'Read the thread first and supply latestTurn.turnId as expectedTurnId,' plus a follow-up check through thread_get. It does not explicitly name alternative tools or state when not to use it, but the operational guidance is strong.

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