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

Annotations already declare destructive, idempotent, and open-world, and the description adds substantial context on top: the disconnect and webhook disable are atomic, privileged scopes are required, the call is revision-guarded, and conversation state has a defined post-condition (inherited conversations return to Kai, explicit handoffs remain). That is exactly the consequential detail a destructive tool needs.

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?

Three dense sentences, front-loaded with the action and its atomic side effect, then prerequisites, then the state consequence. No filler, no restatement of the title.

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 exists, so the description must carry the return semantics, and it partially does by telling the caller what happens to conversations. For a destructive, irreversible operation it covers permissions, atomicity, and revision guarding; the only real gap is behavior on a stale or mismatched expected_revision.

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% for two parameters. The description explains expected_revision as the stored revision (optimistic concurrency) and implies business scoping via 'current business admin membership', but business_id is never named or explained, so half the parameters remain uninterpreted by prose.

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 (disconnect) plus the resource (external agent) and adds a second concrete effect (disable its webhook atomically). The verb is an antonym of the sibling connect_agent, so an agent can route between them without opening a 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 the operational preconditions for calling it (current business admin membership, agents:write, sms:write, webhooks:write) and instructs passing the stored expected_revision. It does not explicitly address when to prefer this over a related operation such as reconfigure or request_agent_update, so no exclusion guidance.

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