kb_validate

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

No annotations are provided, so the description carries the full burden. It never says whether validation is read-only or mutates state, whether a failure blocks downstream tools, what permissions are needed, or what the pass/fail output looks like. 'Quality gate' hints at a verdict but discloses no actual behavior.

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 colon-delimited fragment with no wasted words, but it is under-specified rather than genuinely concise: no verb, no sentence structure, and the reader must parse a bare noun list. Compact but not well-formed.

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 tool with two undocumented parameters, no annotations, and no output schema, the description is far too thin. It does not explain the pass/fail semantics of a gate, the scope of each check, or the interaction with siblings like kb_reconcile, leaving the agent unable to call it confidently.

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 0% for both parameters. The description is completely silent on 'limit' and 'index_check' — it never indicates whether limit caps findings, whether index_check toggles one of the four named checks, or what defaults apply. It does not compensate for the coverage gap.

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 fragment '知识库质量门禁' (knowledge-base quality gate) plus a list of four check categories conveys that this validates KB integrity, but no verb is stated and the name kb_validate has to carry the action. The four checks (structural contract, reference integrity, ledger reconciliation, provenance anchors) give an agent a rough idea of scope, but it is not sharply differentiated from kb_reconcile.

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 statement of when to run this gate, whether it must precede a build/deliver step, or how it differs from kb_reconcile despite the overlapping '状态账目对账' (ledger reconciliation) concern. The agent is left to infer invocation conditions entirely.

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