gmail.users.stop

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

With no annotations, the description carries the full burden and mostly succeeds: it discloses the HTTP POST method, that it is a mutating operation, that it is refused under --readonly safety profiles, and that the API response resource is returned as JSON. It omits auth/scope requirements and whether stopping is idempotent or fails when no watch is active.

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?

The first sentence is crisp and front-loaded, but the trailing boilerplate about building request bodies from typed parameters or body_file does not earn its place for an endpoint with no request body. The sibling list and method/safety note are useful compression.

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 and no annotations, so the description must cover behavior and it does cover method, mutation nature, safety-profile refusal, and response shape. The remaining gap is what the returned resource actually contains for a stop call and any prerequisite that a watch exist.

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 the baseline is 3; the description goes further by explaining the precedence rule ('typed flags win over the params map') and the body_file alternative, which is real semantics the schema alone doesn't express. The generic body-building sentence is largely moot for a bodyless stop endpoints, limiting the lift.

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 ('Turn off push notification delivery for the given user mailbox'), which is precise enough to distinguish it from the sibling 'watch' that does the opposite. No ambiguity about which mailbox is affected.

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 purpose makes the trigger condition clear (stop an existing push notification channel), and it names the same-resource siblings getProfile and watch for orientation. It stops short of explicitly saying 'use watch to enable' or noting whether an active watch is required first.

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