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

Beyond the readOnly/idempotent annotations, the description reveals the dual-path architecture (SEC EDGAR+XBRL vs grounded pipeline), enumerates all possible verdicts, and clearly defines the critical distinction between could_not_verify and unsupported. It adds a direct caller directive not to treat could_not_verify as evidence, which is essential for correct interpretation. 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?

Though lengthy, every sentence carries operational weight. The structure is logical: trigger phrases → when to use → routing → verdicts → error semantics → efficiency gain. The 'IMPORTANT for callers' flag highlights critical caveats without burying them. No filler or 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?

For a complex tool with no output schema, the description provides complete operational context: input types, internal routing, full verdict enumeration, error semantics, and behavioral cautions. It covers both financial and non-financial paths and explains the meaning of each verdict, making it self-sufficient for an agent to invoke and interpret results correctly.

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 schema covers both parameters (100% coverage), so baseline is 3. The description adds meaningful semantics: tolerance_pct's override behavior, the default derived from claim wording capped at 5, and use-case guidance (1–2 for hallucination detection). claim is enriched with concrete examples and the expected natural-language format.

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 opens with concrete trigger phrases ("fact check", "verify the claim that") and explicitly states its function as natural-language claim verification against authoritative sources. It clearly distinguishes from sibling tools by noting it replaces 4–6 sequential calls and details the specific financial versus non-financial scope.

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?

Provides an explicit when-to-use rule ('Use whenever the agent needs to check whether something a user said is factually correct') and contrasts itself with a multi-step alternative. However, it lacks an explicit 'when not to use' case, though the broad 'ANY OTHER factual claim' coverage implies it's always appropriate for factual checks.

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