events

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

'纯读无副作用' merely restates the supplied readOnlyHint=true and destructiveHint=false annotations, so it earns no extra credit. What the description does add is content-level behavior — the five event states that can appear in the queue — but it says nothing about ordering, whether events are consumed/cleared on read, or result shape.

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?

Two short sentences: the resource plus its state enumeration first, the safety profile second. No filler, no repetition of the tool name, and the key identifying information 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 two-optional-parameter read tool with no required args this is close to adequate, but with no output schema the description should say what an event entry looks like (timestamp, session/task reference, message) so the agent knows what it will get back. Pagination and whether events are repeatable across calls are also unaddressed.

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 50% (only 'since' is documented, as 起始时间戳; 'limit' has bounds and a default but no description). The description adds no meaning for limit or since beyond the schema, but with only two simple optional parameters the baseline of 4 applies and the gaps are minor.

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 (读取) and resource (巡检事件队列) and enumerates the event states it surfaces (finished/error/question/stalled/task_failed), which lets an agent distinguish it from minimax_pending or minimax_tasks. It does not explicitly name which sibling to use instead, so it stops short of full differentiation.

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 list of event categories implies the scenario (polling inspection progress/failures), but there is no explicit 'use this when…' statement, no when-not guidance, and no pointer to alternatives such as minimax_tasks or minimax_pending.

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