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

Beyond the read-only/open-world/idempotent annotations, the description details crucial behavioral nuances: the meaning of every verdict, especially distinguishing could_not_verify (check did not happen, contains verification_error, must not be cited as evidence) from unsupported (no source exists). It also discloses the fallback routing, exact percent-delta math, and the pipeworx:// citation output, which the annotations alone do not convey.

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 appropriately front-loaded with query examples and a clear purpose. Each section earns its place: usage trigger, routing, verdict semantics, and a note on efficiency. The only minor inefficiency is overlapping phrasing ('grounded pipeline' vs 'live source'), but overall it remains well-structured and readable.

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 moderately complex behavior, the description is remarkably complete. It defines all return verdicts, explains error states, describes source routing, and specifies the delivery of evidence with citations and reasoning. The agent is fully equipped to interpret results and handle edge cases like could_not_verify.

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 both parameters fully described. The description adds no additional parameter semantics; it references tolerance_pct only indirectly via 'exact percent-delta math' but does not go beyond what the input schema already states. This is the expected baseline when the schema carries the parameter burden.

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+resource ('natural-language claim verification against authoritative sources') with concrete invocation examples ('Is it true that…' / 'fact check'). It clearly differentiates from siblings by explaining it replaces a multi-step pipeline of NL parsing, entity resolution, lookup, and comparison, and uniquely handles both structured SEC and grounded fallback paths.

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 states 'Use whenever the agent needs to check whether something a user said is factually correct' and explains the branching for company-financial vs. other claims. It does not explicitly name alternative tools as better choices for other use cases, but provides clear contextual guidance and even notes it replaces 4–6 sequential calls, signaling when to choose this over manual delegation.

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