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

With annotations present, the description still adds material context the annotations do not carry: activation retires omitted scopes, drops their stored credentials, refuses retired names, and the new revision serves from the next configuration poll. The annotations correctly declare a non-read-only write, but destructiveHint=false understates the disclosed credential-dropping/retirement effect, a nuance the description fortunately corrects for the agent.

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?

Two sentences, zero filler, and the highest-value constraint (the whole scope list must be resubmitted, and activation retires what is left out) is front-loaded before the alternative activation path is described.

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 mutation tool with a deeply nested schema, no output schema, and a large sibling set, the description covers the decisive behavioral facts: destructive activation side effects and the non-idempotent new-revision semantics. It stops short of stating permission/auth requirements or what the call returns, leaving a small residual gap.

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%, so the schema already documents all six parameters, including the nested scope fields and the url/tunnel_id exclusivity. The description mainly echoes the schema (name/URL-or-tunnel/whole scope list) rather than adding syntax or format details beyond it, so the baseline of 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 names a specific verb and resource ("Save a new revision of a gateway server") and enumerates the content of the revision (name, URL or tunnel, whole scope list), then states the side effect (activation unless activate is false). It implicitly separates itself from activate_gateway_server_revision by bundling save+activate, but it never names a sibling or an alternative for the same effect.

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?

It gives one real usage rule, that the entire scope list must be resubmitted on every revision, and explains the activate default. However, there is no explicit when-to-use vs when-to-use-something-else guidance against the many neighboring revision tools (create_gateway_server, activate_gateway_server_revision, archive_gateway_server). Usage is implied rather than stated.

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