stopSubscription

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds concrete behavioral detail beyond the annotations by specifying that closing the subscription releases WebSocket connections and buffers, and that closed subscription IDs become unusable. This helps the agent avoid reusing stale IDs. No annotation contradiction is present.

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 description is two short sentences with no filler. The primary action and immediate consequence are front-loaded, and the second sentence carries the necessary lifecycle warning. Every sentence earns its place.

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 simple one-parameter subscription-stop tool with clear annotations and a complete input schema, the description adequately covers purpose, resource effects, and ID lifecycle. A minor gap is the lack of stated behavior for unknown or already-closed subscription IDs, but this is acceptable given the tool's low complexity and absence of an output schema.

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%: the subscriptionId parameter is already documented as the ID returned by startSubscription. The description adds only minimal parameter-specific meaning, though the 'closed IDs cannot be reused' statement reinforces that the provided ID must be an active subscription. A baseline score of 3 is appropriate given full schema coverage.

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 uses a specific verb ('关闭' / close) with a specific resource ('指定订阅' / specified subscription) and states the concrete consequence: releasing the WebSocket connection and buffers. This clearly identifies it as the termination counterpart to startSubscription and distinguishes it from subscription-creation or listing siblings.

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 description clearly states when to use it: when a subscription should be closed and its WebSocket resources released. It does not name explicit alternatives, but the lifecycle warning that closed IDs cannot be reused implies a required active subscription from startSubscription, which is sufficient guidance for this tool.

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