ingest_event

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

The description discloses key behaviors beyond annotations: backend LLM normalization and grading, requirement for LLM key, and the semantic difference between ingested_by and source. It confirms idempotency (matching annotation) and adds context about the processing pipeline. 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?

The description is detailed but efficient, with each sentence adding distinct value. It uses bold for emphasis and front-loads the core action. While longer than ideal, it is well-structured and avoids 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?

Given the tool's complexity, presence of output schema, and annotations, the description provides sufficient context for an agent to correctly select and invoke the tool. It covers idempotency, identity requirements, and use case boundaries. The only gap is partial parameter documentation.

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 has 0% description coverage; the description partially compensates by clarifying that 'url' and 'title' are required, explaining the difference between 'ingested_by' and 'source', and noting that 'ingested_by' should be the agent's identity. However, it does not explain 'snippet' or 'published_at', leaving some parameters ambiguous.

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 tool's purpose: to feed financial news into an event ledger, with backend processing, normalization, and grading for committee RAG recall. It distinguishes from sibling tools (none of which are similar ingest tools) and specifies its use for news related to user holdings, especially from Chinese sources.

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 provides explicit usage guidance: use when the agent finds news related to user holdings, especially from Chinese sources and regional markets where crawlers are weak. It also notes idempotent behavior and the requirement for a backend LLM key, helping the agent decide when and how to invoke the tool.

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