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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, but the description adds crucial behavioral detail beyond this: the meaning of each verdict (especially could_not_verify vs. unsupported), the presence of verification_error{stage,detail} for failures, the routing logic, and the explicit warning that could_not_verify is not evidence for/against the claim. This is rich, non-contradictory context that greatly aids correct interpretation.

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 dense but every sentence earns its place: usage triggers, routing behavior, return values, and critical error semantics are all covered. It is front-loaded with examples and immediately tells the agent when to use the tool. The structure flows logically from what it does, to how it works, to what it returns and what to be careful about.

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, the description comprehensively explains return values (verdict list, actual value with citation, reasoning, verification_error). It also covers the two execution paths, the distinction between could_not_verify and unsupported, and even mentions the efficiency benefit over sequential calls. Combined with full parameter schema coverage and supportive annotations, this is complete for safe and correct invocation.

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%, so the baseline is 3. The description adds meaningful guidance for tolerance_pct, explaining how it overrides the default implied by claim wording (capped at 5) and recommending 1–2 for hallucination detection. It also clarifies that 'claim' is a natural-language factual statement, reinforcing the schema's examples. This goes beyond a simple restatement of parameter names.

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 identifies the tool as natural-language claim verification against authoritative sources, with concrete query examples ('fact check', 'verify the claim that…'). It distinguishes itself from siblings by explaining the two routing paths (SEC EDGAR/XBRL for financial claims, grounded pipeline for everything else) and its role as a replacement for 4–6 sequential calls.

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 explicit usage guidance: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains when the financial fast path applies versus the general grounded pipeline. However, it does not explicitly name alternative tools or state when not to use it (e.g., when deep research is needed), leaving some ambiguity in tool selection.

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