wb_query

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

With no annotations, the description must carry the full behavioral burden. It does disclose read-only safety, which is useful, but this is contradicted by the confirm parameter description stating that write commands like add/done/edit/del can be accepted with confirm=true. This internal contradiction leaves agents unable to trust whether writes are truly impossible.

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 dense sentence front-loads the core purpose ('全域只读调阅'), then packs in command families, covered domains, and the doctor self-check role. There is no filler or repetition; every clause contributes actionable information.

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 broad tool with no output schema and no annotations, the description covers scope, command families, domains, and safety posture remarkably well. The main gap is the unresolved read-only vs. confirm/write contradiction, plus the absence of any return-format or error-behavior notes, but the rich input schema compensates for most invocation details.

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%, so the baseline is 3, but the main description adds meaning beyond the schema by enumerating the valid command families and the data domains they map to. This directly helps agents construct the command parameter, which the schema itself points back to via '各域允许的首词见 tool description'.

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 opens with '全域只读调阅' (global read-only retrieval), states the exact verb and resource scope, and lists the command families plus the 49-table AI-workbench coverage. The read-only framing clearly distinguishes it from the write-oriented sibling tools even though no sibling is named.

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 makes the primary usage context clear: use this tool for cross-domain read-only retrieval across the AI workbench, with doctor for environment self-checks. It does not explicitly name alternatives or say 'do not use for writes,' but the read-only scope is a strong implicit exclusion.

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