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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description goes well beyond them: it names exactly what stops working, states the activation timing ('takes effect on the next call'), notes immediate channel propagation, reassures that audit logging continues, and flags the organization API key requirement. That is exactly the extra behavioral context the annotations cannot carry.

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?

Front-loaded with the imperative action, then consequences, then timing, then the auth prerequisite — a sensible priority order with no filler. The first sentence is slightly overloaded with a colon-led list, but every clause carries distinct information.

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, org-scoped kill switch with no output schema, the description covers effect scope, latency, reversibility path, audit behavior, and auth requirements. An agent has everything needed to decide and to call it correctly given the two optional parameters.

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 100%, with both parameters fully documented including the '*' wildcard semantics and where the reason string is surfaced. The description implies the target is 'an agent' but adds no format or default information beyond the schema, so the baseline 3 is right.

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 an agent at once') and immediately enumerates the blast radius (mandate_spend, gateways, room messages). It also names the counterpart tool live_resume, so an agent can distinguish it from sibling lifecycle tools like live_status or live_info without reading schemas.

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 kill/resume pairing with live_resume gives clear context for when this tool is the right one, and the 'at once' framing signals emergency use. There is no explicit when-not-to-use guidance or discussion of narrower alternatives for a single gateway (e.g. gateway_set_guard), so it falls short of a 5.

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