kb_health_check

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

No annotations are provided, so the description carries the full behavioral burden. It makes clear the tool reports rather than mutates, and it lists exactly which conditions are surfaced, which is useful. However, it does not state cost/scope of the scan (whole KB vs. partial), whether it modifies anything (e.g. rebuilding the index), or any performance caveats for large knowledge bases.

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?

Two short parts: a one-line purpose followed by a dense enumeration of the checks, with the purpose front-loaded. Every clause maps to a distinct output category. Minor waste only in the reST-style double-backtick markup around `_Inbox` and `INDEX.md`.

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?

With zero parameters and an output schema present, the description only needs to explain what the audit looks for, and it does so exhaustively across four categories. The remaining gap is operational context — expected cost on a large KB and whether any remediation happens — but nothing required to invoke it 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter-level gaps exist to compensate for.

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 gives a specific verb+resource ('audit the knowledge base') and then enumerates the four problem classes it reports: inbox backlog, orphans, dead links, and unindexed files. This is far more than a restatement of the name. It does not explicitly contrast itself with overlapping siblings such as kb_status, kb_scan_inbox, or kb_reindex, so an agent must infer the boundary.

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?

Usage is implied rather than stated — 'audit for common problems' suggests a periodic or pre-cleanup diagnostic, and the enumerated checks hint at what you'd act on afterwards. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g. kb_scan_inbox for inbox-only checks).

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