Ingest Knowledge

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

Describes idempotency via externalId and optional LLM processing, adding context beyond annotations (idempotentHint=true). No contradictions with 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?

Two concise sentences, front-loaded key info. No wasted words.

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?

No output schema; description lacks information about return values or errors. Adequate for input behavior but could be more complete about post-ingest results.

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 100%, but description adds meaning by explaining dedup usage and processing modes (summarize, extract_facts, custom). Enhances understanding beyond property descriptions.

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 'Ingest content into a knowledge base' and mentions key features (deduplication, optional LLM processing). Distinguishes from siblings like neuron_create_kb_entry by highlighting dedup and processing.

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?

Implied usage through dedup and processing options, but no explicit when-to-use or when-not-to-use guidance compared to alternatives (e.g., create_kb_entry, sync_knowledge).

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