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

Annotations already declare readOnly/openWorld/idempotent, so the description adds value by detailing fallback routing, verdicts, and the critical call-out that could_not_verify means the check did not happen and must not be treated as evidence. It also discloses error payload structure (verification_error{stage,detail}) and unsupported semantics, which goes beyond annotation basics.

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 longer than typical but intentionally packs in user-trigger phrases, routing logic, verdict outputs, and an important error-handling caveat front-loaded with 'IMPORTANT for callers.' It is well-structured, though some parts (e.g., full verdict list) could be trimmed if an output schema existed.

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 no output schema and multi-path complexity, the description covers return verdicts, citation format, reasoning, error handling, and the tool's role as a composite replacement for sequential calls. It leaves no major ambiguity for an agent deciding whether to invoke it.

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%, with full descriptions for both claim and tolerance_pct. The description adds peripheral context like 'exact percent-delta math' but does not elaborate on parameter semantics beyond what the schema already provides, so baseline 3 applies.

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?

Description explicitly defines the tool as natural-language claim verification against authoritative sources, with trigger phrases like 'fact check' and 'verify the claim that…'. It clearly distinguishes from siblings by describing the structured SEC EDGAR path for company-financial claims and the grounded pipeline for other 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?

Provides an explicit when-to-use: 'Use whenever the agent needs to check whether something a user said is factually correct.' It differentiates internal routing (company-financial vs other) but does not name alternative tools to use instead, so exclusions are mostly implicit.

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