查询即梦队列摘要

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

Annotations already declare readOnly, idempotent, non-destructive, open-world. The description adds that counts come from persisted state rather than a live upstream call, which hints at possible staleness, but it does not state how fresh that snapshot is or what the response looks like. Useful context beyond annotations, but thin.

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?

A single semicolon-delimited sentence that front-loads what is returned and ends with the boundary condition. Every clause carries information; nothing is redundant.

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 zero-parameter, non-destructive read with no output schema, the description covers enough: the three categories of data returned. It does not describe the shape of the counts or queue lists, which is the only remaining gap, and with no output schema the agent might want that.

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 tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly gives no parameter guidance, which is appropriate.

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 names a specific verb (查询) and the exact data returned: persisted state counts, read/write queues, and earliest queue time. An agent can form a clear picture of what the tool produces, though it does not distinguish itself from siblings like list_jobs or capabilities.

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?

Usage is only implied: the note '不发起上游操作' signals this is the safe way to inspect queue state without triggering upstream work. It never names alternatives such as list_jobs or get_job, nor states when this should be preferred over them.

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