agent_next

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

"认领" (claim) describes taking ownership of a queue item, which changes local state so other agents no longer see it as pending — a write. The annotations declare readOnlyHint=true and destructiveHint=false, so the description contradicts the declared safety profile. It also omits whether claiming is reversible, what happens if no pending items exist, and whether the claimed item can be released.

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?

One front-loaded sentence states the action first, with the explanatory parenthetical second; there is no filler. It is tight, though the parenthetical's phrasing ("本该发给 API 的完整请求") is opaque enough to require a re-read.

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 queue-consuming tool with no output schema, the description does not say what the returned payload looks like, how the agent is expected to answer the claimed request, what happens on an empty queue, or whether the claim expires. An agent cannot complete the intended workflow from this definition alone.

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 description coverage is 100% and both parameters are optional strings with their own descriptions (project root, workdir default), so the schema already carries the semantics. The tool description adds nothing about resolution order or how project/workdir interact with the claimed item, so the baseline 3 applies.

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?

Names a concrete action and object: fetch the oldest pending order and claim it, with a parenthetical that explains the underlying flow (a request that would have gone to the API is answered locally by the agent using its own quota). That is much more than a restatement of the name and lets an agent distinguish it from agent_submit/agent_status, though the sibling relationship is only implied.

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 explicit when-to-use guidance: no statement of when to call this versus agent_status or agent_submit, no preconditions (must a project/workdir exist first?), and no mention of what to do with the fetched item afterwards. The parenthetical hints at context but never states the trigger or the follow-up.

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