startSubscription

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

The description goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) by disclosing specific behavioral traits: background message accumulation, auto-close after 5 minutes without readMessages access, and support for multiple independent subscriptions on the same topic. These details are not present in the annotations or schema and are critical for correct usage.

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 compact and information-dense, with each of the four sentences contributing a distinct, necessary fact: what the tool does, what it returns, the timeout behavior, and concurrency semantics. There is no redundant or filler content, and the most important functional statement is front-loaded.

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 subscription-starting tool with no output schema, the description adequately covers the return value (subscriptionId) and the required follow-up calls (readMessages/stopSubscription). The 5-minute timeout and per-topic multiplicity are also covered. Minor gaps include the lack of explicit limits on the number of concurrent subscriptions and any mention of authentication requirements, though the latter is partially addressed by the requiresAuth parameter description.

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?

The input schema already provides 100% parameter coverage with descriptions for topic, category, maxMessages, and requiresAuth. The description adds no parameter-specific meaning beyond what the schema provides, so the baseline of 3 applies. It does not clarify formats or defaults beyond schema, but the schema is already descriptive.

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 states a specific action ('开启' - start) applied to a distinct resource: a persistent WebSocket subscription that accumulates messages in the background. It clearly differentiates from the many sibling subscribe* tools by emphasizing the persisted buffer and the returned subscriptionId, which is central to the tool's purpose.

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 provides a clear workflow: start the subscription, then use readMessages and stopSubscription with the returned subscriptionId. It also highlights the 5-minute inactivity timeout, which is essential usage guidance. However, it does not explicitly state when to choose this over the sibling subscribe* streaming tools, so the agent must infer that this is for buffered/queued retrieval rather than real-time streaming.

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