document_ingest

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

Describes background async behavior, file persistence details (pypdfium2, PyMuPDF, Docling), and sidecar location. No annotation contradictions. Less transparent about error behavior and resource side effects.

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?

Single paragraph with front-loaded purpose and parameter details. Dense but not verbose. Could be slightly more structured (e.g., bullet points), but 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?

Covers main purpose, parameters, and output via output schema. Lacks prerequisites (e.g., file existence), error handling, and relationship with status tools. Adequate given complexity.

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%, but description explains path, root, doc_id, profile, and library_scan behavior. Misses force parameter, and library_scan is described but not in schema. Partial compensation for low schema coverage.

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 verb 'Queue high-fidelity background ingest' and the resource 'one EPUB/PDF document'. It distinguishes from siblings like library_ingest_documents by specifying single document ingestion.

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 guidance on when to use doc_id vs path, root, and profile options (auto, book, paper). Includes recommendation for library_scan for automatic profile detection. Does not directly compare to list/status siblings but context implies single ingest use.

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