learn_document

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

Describes advanced processing steps: REAL semantic chunking, structure preservation, denoising, metadata extraction, fallback system, and saving a copy for verification. No annotations, so description carries full burden; it discloses key behaviors without contradicting any 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?

Description is somewhat long but well-structured with bullet points for supported types, features, and examples. Front-loaded with purpose; each section adds value without redundancy.

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?

Covers input, processing behavior, and outcome (stored in knowledge base with metadata, copy saved). Output schema exists, so return values not needed. Could mention idempotency but overall complete.

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?

Single parameter file_path is explained as 'absolute or relative path' in the description, adding meaning beyond the schema's type string. Schema coverage is 0%, so description compensates well.

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?

Clearly states the tool reads and processes document files using advanced semantic chunking and adds to knowledge base. Distinguishes from sibling learn_text by specifying document file types and advanced features.

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 context on when to use (train AI on document files) and lists specific use cases. Does not explicitly exclude alternatives, but implied by focus on structured documents.

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