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

Annotations already cover readOnly, idempotent and non-destructive, so the bar is lower. The description still adds real behavioral context beyond them: the owner-scoping rule for non-owned KBs and the crucial workflow constraint that publish_kb is a full replacement where omitted pages disappear. It stops short of describing pagination or size limits on returned content.

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-loaded with purpose then parameter semantics, with no filler sentences. It is dense in a single block, which slightly hurts scannability, but every clause (alias note, owner rule, publish_kb warning) carries information an agent needs.

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 5-parameter, zero-required, alias-heavy read tool with no output schema, the description covers return content ('版本和页面清单', '那一页的原文'), scoping rules, and the update-safety workflow. Nothing essential to correct invocation is missing.

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% (baseline 3), and the description still adds value by specifying which parameters combine in which case (name only vs name+page vs plus owner) and by tying owner to the ownerKey value shape from list_kbs. The alias parameters path/kbName are left to the schema.

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+resource ('读一个知识库') and immediately differentiates it from siblings by explaining that name alone returns version+page list and name+page returns page content, contrasting with publish_kb. An agent can tell read_kb apart from list_kbs and publish_kb without opening a 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 explicit conditional usage: pass only name for the manifest, add page for raw content, add owner for workspace/shared KBs, and read existing pages before updating because publish_kb replaces the whole KB. This is a complete when/how/alternative-avoidance guide.

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