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

Annotations already declare destructive=true and idempotent=true, but the description adds real value beyond them: URLs stop working immediately, and gateway history is retained in the log. That clarifies what is and isn't destroyed, plus the org-API-key auth requirement. It doesn't say whether the gateway can be re-enabled or what the response contains.

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 short sentences, front-loaded with the core action, then effect, then prerequisite. Every sentence carries distinct information with no repetition or filler.

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 one-parameter tool with no output schema and rich annotations, the description covers effect, data retention, and auth. It could go one step further and state whether the disable is reversible or how the tool relates to gateway_create, but nothing critical to correct invocation is missing.

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% for the single gw_id parameter ("gw_... ID"), so the schema already carries the semantics. The description adds no format, prefix, or lookup guidance beyond what the schema provides, so baseline 3 applies.

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 gives a clear verb+resource ("Turn a gateway off") and its operational effect, so an agent can tell it apart from gateway_create/gateway_info/gateway_list at a glance. It stops short of explicitly naming a sibling it must not be confused with, and the framing as "turn off" rather than "delete" is left for the reader to reconcile with the tool name.

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?

"Requires the organization API key" is a useful precondition, but the description offers no when-to-use vs when-not guidance and never points to any sibling (e.g. gateway_set_guard, gateway_create). Usage is only implied by the destructive effect described.

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