get_doc_health

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

With readOnlyHint=true already in annotations, the description adds value by enumerating the diagnostic dimensions (BM25 corpus sanity, embedding coverage, drift status) and clarifying scope. The semantic caveat that index health is orthogonal to content correctness is genuinely useful behavioral context. It doesn't cover cost or error behavior of a potentially expensive aggregate query, but is strong for a read-only tool with good annotations. No contradiction with annotations.

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?

Exactly three sentences, purpose-first front-loading, each sentence earns its place. The long list of return fields is justified and enumerates scope. Ends with a distinct value-add caveat. No repetition of the tool name or fluff.

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 single-parameter, read-only tool with no output schema, the description covers the diagnostic scope and its semantic limits quite thoroughly. The only gap is the relationship between `repo` and 'index'—readers must infer that the repo contains the index being diagnosed. A clarification of what the tool returns for invalid/missing repos would round it out.

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% and the description provides zero explanation of the `repo` parameter, which must have compensated for this gap. The description consistently uses 'index' while the parameter is `repo`, possibly implying the mapping (repo's index) but leaving it to inference. With a single parameter and no documentation, this is a meaningful gap in an otherwise clear 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 phrase 'One-shot index health diagnostics' combined with a concrete list of returns (section_count, doc_count, role_distribution, drift status, etc.) makes the tool's purpose specific and concrete. The disclaimer 'Diagnoses the index, not the writing' differentiates it from content-quality analysis, helping to distinguish from similar-sounding siblings like doc_health_radar. However, the verb is nominalized ('diagnostics' rather than an action) and no sibling is explicitly named, so it slightly misses a perfect score.

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?

'One-shot' signals this is a single-call comprehensive health check, giving the agent a clear sense of when to use it. The caveat 'a healthy report says nothing about whether the docs are correct' provides a helpful when-not-to-rely-on-it boundary. However, no alternative tools are named, and there is no explicit 'use X for content quality' pointer despite ~80 siblings existing.

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