eda_sys_message_bus_subscribe_once_public

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

With no annotations, the description carries the behavioral disclosure burden. It states that the subscription is one-time ('订阅单次消息'), which is useful, and that it returns a message bus task (ISYS_MessageBusTask). However, it does not disclose whether the subscription auto-unsubscribes after the first message, what happens if the topic is missing, whether the callback can be cleaned up, scope of 'public' (global vs per-window), or any side effects. The return type is mentioned but not elaborated.

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 very short: a C-style signature, a one-line Chinese summary, and a return type. It earns space by being compact, but the structure is front-loaded with a signature that duplicates the tool name and misses key behavioral details. It is not bloated, but it is under-specified rather than efficiently complete.

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 tool with no annotations and no output schema, the description is insufficiently complete. It does not explain the lifecycle of the one-time subscription, whether the returned task can be used to cancel, how the callback is delivered, or how to use windowId correctly. The sibling set includes closely related subscribe/publish/pull variants, making this lack of context more damaging.

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% for the wrapper fields (args, windowId), but the real parameters are inside args, which has generic items with an empty schema. The description does list the official signature containing topic and callbackFn, which adds meaning, but it does not explain the expected types or format of each argument beyond the signature string. The callback semantics (message: any) are implied but no guidance on how to serialize or pass a function through args is given.

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 the specific operation: subscribe once to a public message bus topic (sys_MessageBus.subscribeOncePublic), and includes a Chinese line clarifying it's a public message bus for single-message subscription. It is distinguishable from siblings like subscribe, subscribe_public, and subscribe_once by name and the 'public' and 'once' qualifiers, though it does not explicitly contrast with those 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?

There is no guidance on when to use this tool versus subscribe_public, subscribe_once, pull, or rpc_call variants. The description does not explain when a one-time subscription is preferable, how long the subscription lasts, or whether it should be used over a persistent subscription or a pull. Agents must infer usage entirely from the tool name.

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