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

Discloses all side effects: marks tweets reviewed, upserts analyst_calls with extraction='llm', overrides heuristic row, and states idempotency. With no annotations provided, the description fully compensates.

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 two paragraphs; the first sentence is a clear summary. The second paragraph conveys necessary details but could be more structured (e.g., bullet points). Still efficient with no fluff.

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 complex nested parameter and the presence of an output schema (referenced with return fields), the description covers all essential aspects: what it does, side effects, parameter format, and return value. It is self-contained.

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?

Even though schema coverage is 0%, the description thoroughly explains the verdicts parameter structure, including all nested fields (tweet_id, verdicts array with ticker, is_call, direction, etc.). This provides complete semantic meaning beyond the raw schema.

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 persists LLM direction verdicts from a direction_review_batch, distinguishing it from its sibling tool which likely generates the verdicts. The action is precise: 'persist' as a verb with specific resource.

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?

Explicitly marks as OPERATOR-ONLY, providing a clear usage restriction. Context from siblings implies it should be used after direction_review_batch, but no explicit when-not-to-use or alternatives listed.

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