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

The description discloses that the tool flips the conversation to open to drop late webhooks, and that the interruption is best-effort, indicating potential failure. This goes beyond the annotations (which only state non-idempotent and non-destructive) by detailing side effects and limitations, though it does not cover all possible error conditions.

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 two sentences long, concise, and directly addresses the tool's action and effect. No redundant information is included, and the structure is logical.

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?

The description provides sufficient context for an agent to understand the tool's purpose and effect, including the state change and best-effort nature. However, it does not explain how to determine if a turn is in-flight or what happens if the turn is not in-flight, leaving minor contextual gaps. Given there is no output schema, this is adequate.

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?

Both parameters are required UUIDs, but the schema provides no descriptions and the description adds no semantic detail beyond the parameter names. While the names process_id and conversation_id are self-explanatory, the tool does not clarify their exact roles or relationship to the artifact-chat turn.

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 clearly states that the tool stops an in-flight artifact-chat turn, which is a specific verb (stop) and resource (artifact-chat turn). It also explains the action of flipping the conversation back to open, distinguishing it from deletion. This is precise and unambiguous.

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 implies usage when a turn is in-flight and needs to be halted, and contrasts with deletion by noting it only flips to open. However, it does not explicitly name sibling tools like deleteClarityArtifactChatConversation, so the distinction is implicit rather than explicitly stated.

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