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

Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds critical semantics beyond that, particularly the warning that 'could_not_verify means the check did not happen... must not be shown as one,' and distinguishes it from 'unsupported.' It also discloses the two routing paths and the verdict set, which is valuable and goes beyond what annotations provide. No contradiction 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 long but well-structured, starting with trigger phrases and purpose, then explaining execution paths, return values, and caveats. Each sentence adds necessary information; the complexity of the tool justifies the length, though a slight tightening of the concluding sentence about replacing sequential calls would improve conciseness.

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?

For a tool with no output schema and two complex execution paths, the description thoroughly covers the return structure (verdict types, value with citation, reasoning), the interpretation of verdicts (including the dangerous could_not_verify case), and the fallback behavior. This is sufficient for an agent to invoke the tool and correctly handle the response.

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% for both parameters, so the baseline is 3. The description enhances this by explaining tolerance_pct usage ('set 1–2 for hallucination detection where any material error must be refuted') and clarifying that the claim is a natural-language factual claim, complementing the schema examples.

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 this is a claim-verification tool with a specific verb ('verify') and resource ('authoritative sources'). It provides trigger phrases, distinguishes two execution paths (SEC EDGAR/XBRL for financial claims vs grounded pipeline for others), and differentiates itself from sibling tools like ask_pipeworx or deep_research by focusing on fact-checking claims.

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?

It explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct.' It also notes that it replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → comparison), implying it should be used over chaining other tools. However, it does not explicitly name alternatives or describe scenarios where a different tool would be better.

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