library_explore

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

No annotations are provided, so the description carries full burden. It discloses key behaviors: operates on already-ingested sidecars, uses local SQLite FTS and DocumentGraph ranking, and does not auto-ingest PDFs. Missing details like performance implications or required permissions, but still adds value.

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?

The description is concise with three sentences, each adding distinct information. It front-loades the purpose and usage. Could potentially include parameter info without being verbose, but as is, it's efficient.

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?

Given that output schema exists, return value documentation is not required. However, with three parameters and 0% schema coverage, the description fails to cover parameter semantics adequately. The tool is relatively simple, but missing parameter details reduces completeness.

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 0% (no parameter descriptions in schema). The description partly explains 'root' (default behavior) but does not describe 'query' or 'top_k' at all. This leaves the agent without guidance on parameter usage, a significant 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 description clearly states the tool's purpose: exploring an already-ingested root sidecar using SQLite FTS and DocumentGraph ranking to find relevant content in books/papers. It distinguishes from sibling tools like document_explore and library_ingest_documents by focusing on querying ingested content.

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?

The description explicitly says when to use the tool ('when the user asks which book/paper contains relevant content') and explains default behavior for root. It also notes that it does not auto-ingest heavy PDFs, providing context for what not to expect. However, it does not compare to alternatives or specify when not to use.

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