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

The annotations already declare readOnly, openWorld, idempotent, and non-destructive hints, and the description adds substantial behavioral detail beyond that: the meaning of each verdict, the critical caveat that could_not_verify means the check did not happen and must not be treated as evidence, verification_error structure, and the grounded pipeline's verbatim evidence handling. 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 a single dense paragraph but every sentence earns its place: purpose, routing, return values, critical caller warning, and efficiency benefit. It is well-structured with clear sections, though slightly long. No redundant 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?

Despite having no output schema, the description covers the full behavior: what the tool does, when to use it, how it routes claims, what it returns (verdicts, actual value, citation), and critical error semantics. It is complete for an agent to select and invoke correctly, especially alongside 40+ siblings.

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%, but the description adds significant meaning: tolerance_pct overrides the implied tolerance and explicitly recommends values for hallucination detection, and the claim examples clarify the expected input. This goes beyond the schema's basic descriptions, earning a score above the baseline.

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 uses a specific verb ('verify') and resource ('natural-language claim verification against authoritative sources'), with clear examples of trigger phrases. It distinguishes itself from siblings by explicitly stating it replaces 4–6 sequential calls and details the structured vs grounded pipeline, making its unique purpose unmistakable.

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 explicitly states when to use: 'Use whenever the agent needs to check whether something a user said is factually correct,' and provides clear routing rules for company-financial vs. other factual claims. It also implies alternatives by noting it replaces sequential NL parsing, entity resolution, data lookup, and comparison steps, giving strong usage context.

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