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

Annotations already declare destructive=true, idempotent=true, readOnly=false, openWorld=false, so the safety profile is covered. The description adds real value beyond that: it clarifies that the operation replaces the entire existing assignment, that non-conforming KBs are dropped rather than erroring (reported via kbDropped), and that changes take effect immediately. It does not contradict any annotation.

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?

Front-loads the core action and replacement semantics, then packs parameter grammar, drop behavior, and effect timing into a single dense paragraph. Every clause carries information, though the parentheticals and multiple semicolon-separated clauses make it slightly heavy.

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 2-parameter mutation tool with no output schema, the description covers the essentials: value format, authorization prerequisite, [] semantics, dropped-entry feedback (kbDropped), and immediate effect. It omits what happens on an invalid slug or an overall error/return shape, which is a minor gap given annotations already carry the destructive/idempotent profile.

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?

With only 50% schema coverage (slug has no schema description), the description compensates well: it marks slug as required and, more importantly, defines the value grammar for kbs — bare library name for owned KBs, list_kbs ref (e.g. ws:xxx/库名) for workspace/shared KBs — plus the [] empty-list semantics. Only minor detail on slug validation is absent.

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 and resource — 设定一个岗位用哪些知识库 — and adds the critical scope qualifier 整体替换 (full replacement), which is not covered by the title alone. This is functionally distinct from every sibling (list_kbs, publish_kb, read_kb, get_staff_config), so an agent can identify it without opening the schema.

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?

Gives concrete usage conditions: how to format each kbs entry (bare name for own KBs vs. list_kbs ref for workspace/shared KBs), that [] means no KBs, and that unauthorized shared KBs are silently ignored. It references list_kbs as the source of refs but never states explicitly when to prefer this tool over patch_staff_config or get_staff_config for staff configuration.

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