Delete an agent conversation

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

Annotations declare the destructive/idempotent profile, and the description adds non-obvious behavior on top: a dry-run mode without confirm, that an in-flight turn is deleted rather than stopped, that memory is reset for that session, and what is left untouched (model outputs, saved workflows, Studio display name). That is substantive disclosure beyond the annotation block.

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?

Purpose is front-loaded in the first clause, followed by the confirm gate, the running-turn caveat, and the exclusions in descending priority. No filler; every sentence carries a constraint or a consequence an agent needs.

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 tool with an output schema available, the description covers the full decision surface: consent gating, alternative action, undeletable case, and blast radius. An agent could call this safely without consulting anything else.

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 coverage is 100%, so agent/session/confirm are already documented at baseline 3. The description adds real semantics the schema only gestures at: confirm acts as a describe-then-delete gate requiring user consent, and session validity depends on the agent ("default" session undeletable).

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?

Opens with a specific verb+resource: "Permanently delete one conversation (session)" and names the exact targets (Studio, Workflow Agent, deployed agents). It is clearly distinguishable from delete_agent (whole agent) and cancel_agent_message (stop, don't delete).

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?

Explicitly covers the when-not path: "Without confirm: true it only describes what would be deleted; ask the user before confirming," names the alternative "cancel it first with cancel_agent_message," and states the exclusion "The Workflow Agent's 'default' session cannot be deleted." It even points at get_agent_conversation as the way to check for a running turn.

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