knowledge_ingest

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

Without annotations, the description discloses several behavioral traits: files already in raw/ are skipped, index is rebuilt once after digest_write, auto-classification and auto-routing occur, and timestamps are added. It also details the extraction process (per-page PDF, per-sheet XLSX, etc.). However, it doesn't mention side effects like overwriting existing data or security/auth requirements.

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 well-structured with clear sections for each mode and bullet points for parameters. It is concise, with no extraneous information, and every sentence adds value. However, it could be slightly more condensed without losing clarity.

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 the complexity (9 parameters, two modes, no output schema, no annotations), the description is fairly complete. It explains the overall pipeline, each mode's workflow, and key behaviors like file skipping and index rebuilding. It lacks an explanation of the return value or output format, but the absence of an output schema lessens the need.

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?

The input schema already provides 100% description coverage for all 9 parameters. The tool description adds value by explaining the purpose of the mode parameter and summarizing the role of batch parameters (e.g., 'Scans a directory... imports to raw/'). This contextualizes the parameters beyond their schema definitions.

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 it is a knowledge ingestion pipeline with two distinct modes: batch (import, extract, chunk, pack) and digest_write (write LLM summaries to wiki). It differentiates from sibling tools like raw_ingest (which only imports raw files) and wiki_write (which only writes pages) by covering the full ingestion and summary writing process.

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 explains when to use each mode: batch for importing and packing source documents, digest_write for writing wiki summaries. However, it does not explicitly state when not to use the tool or mention alternative tools like raw_ingest for simpler raw file imports. The context is clear but lacks explicit exclusion criteria.

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