eda_sys_message_bus_subscribe

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

With no annotations provided, the description carries the full burden. It discloses that the subscription is persistent and that it returns a message bus task, which hints at handle-based management. However, it does not explain cleanup, whether the bus must already exist, or callback invocation semantics.

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 front-loads the essential signature before the Chinese summary. The 'remarks' and 'returns' fragments add useful info without padding, though the structure is slightly terse.

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?

The description covers the core subscribe action, persistence, and return type, but omits important operational context such as whether a private message bus must be created beforehand, how to unsubscribe using the returned task, and topic requirements. Given the absence of annotations and output schema, these gaps are material.

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 schema only provides a generic args array, but the description's function signature explicitly defines the two parameters (topic: string, callbackFn: (message: any) => void) and their order. This meaningfully compensates for the schema's opacity.

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 clearly states the action ('subscribe'), the resource ('private message bus'), and includes the full function signature. The '私有消息总线' and '持久性订阅消息' qualifiers distinguish it from sibling tools like eda_sys_message_bus_subscribe_public and eda_sys_message_bus_subscribe_once.

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 clear context: it is a private, persistent subscription, from which an agent can infer it is not for public buses or one-time subscriptions. However, it does not explicitly name alternatives or state when-not-to-use conditions.

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