library_scan

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

With no annotations, the description carries full burden. It discloses the main behavioral traits: recursive scanning, sidecar catalog registration, and return performance metrics. However, it does not mention whether the operation is destructive, if it can be safely rerun, or any permissions needed. This is adequate for a non-destructive scan tool but lacks depth.

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 sentences, no fluff. The first sentence delivers the core purpose and mechanism; the second adds usage guidance and return value info. Every sentence earns its place. Highly 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 an output schema exists, the description appropriately references return fields (candidate counts, hash workers, scan timing). The tool has two optional parameters; one is well-explained. The sibling tools set context. It covers the essential aspects for an agent to decide to invoke it, though a tiny bit more on patterns would make it perfect.

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%, so description must compensate. It explains the 'root' parameter ('If root is omitted, the MCP process project root is used') but says nothing about the 'patterns' parameter. Users need to guess its purpose (likely file patterns). This is a significant gap, as one of two parameters is completely undocumented.

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 action ('Scan a local root recursively for EPUB/PDF documents'), the target resource ('local root'), and the outcome ('register them in one root sidecar catalog'). It uniquely describes what the tool does and distinguishes it from sibling tools like library_explore or library_ingest_documents.

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?

Provides explicit usage guidance: 'Use this before doc_id-only tools after a fresh server restart.' It tells when to use it, though it does not explicitly state when not to use it or mention alternatives. The context of sibling tools helps, but a bit more guidance on idempotency or avoiding unnecessary scans would elevate it.

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