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

Annotations already signal read-only, idempotent, and non-destructive behavior. The description adds rich behavioral context: two verification pipelines, the exact verdict set (confirmed, approximately_correct, refuted, inconclusive, unsupported, could_not_verify), the presence of a verification_error field, and critical caller guidance that could_not_verify must not be treated as evidence for or against the claim. It also clarifies the difference between unsupported and could_not_verify. 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 longer than typical, but it is front-loaded with example queries and every sentence carries useful information (usage, pipelines, verdicts, error semantics). It is well structured, but the length (especially the detailed path explanations and the lengthy caller warning) keeps it from a 5, which would be reserved for a truly minimal yet complete description.

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 the tool's complexity (two verification paths, multiple verdict values, error handling) and the absence of an output schema, the description is remarkably complete. It covers return content (verdict, actual value, citation, reasoning), explains failure modes (could_not_verify vs unsupported), and gives practical invocation guidance. An agent has enough to invoke and interpret the tool 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?

Schema coverage is 100% — both `claim` and `tolerance_pct` have clear, detailed descriptions in the input schema. The tool description itself does not add substantial parameter-level meaning beyond what the schema already provides; it mentions tolerance semantics indirectly via "exact percent-delta math" but the schema already explains defaults and overrides. 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?

The description clearly states that the tool performs natural-language claim verification against authoritative sources, with explicit example phrasings like "fact check" and "verify the claim that…". It distinguishes itself from siblings by describing a two-path pipeline (SEC EDGAR for company financials, grounded pipeline for all other facts) and noting it replaces 4–6 sequential calls, so the agent knows exactly what this tool is for.

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 says "Use whenever the agent needs to check whether something a user said is factually correct," which is a clear invocation guideline. It also explains that company-financial claims follow a fast path and any other claim falls through to the grounded pipeline. However, it does not name alternative tools or explicitly state when not to use it, so it stops short of a 5.

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