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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds critical behavioral nuance beyond this: the dual verification paths (SEC EDGAR/XBRL vs. grounded pipeline), the meaning of each verdict, and especially the important distinction between 'could_not_verify' (check did not happen) and 'unsupported' (no source covers it). This is exactly the kind of context annotations cannot capture.

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 average but every sentence carries substance: examples, core purpose, routing logic, verdict semantics, and the crucial caller warning. It is well-structured with a clear flow. It could be slightly tighter without losing value, but it earns a 4 for being information-dense rather than padded.

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 fully describes return values (verdict, actual value with citation, reasoning) and explains edge cases ('could_not_verify' vs 'unsupported'). It also covers the tool's composite nature (replacing 4–6 sequential calls). For a 2-parameter tool with no output schema, this is complete.

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 good descriptions for both 'claim' and 'tolerance_pct'. The description adds value beyond the schema by advising to set tolerance_pct to 1–2 for hallucination detection and explaining the default is implied by wording, capped at 5. This practical guidance helps the agent choose parameter values correctly.

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 ('validate', 'check', 'verify') with a clear resource ('natural-language factual claims against authoritative sources'). It explicitly distinguishes itself from alternatives by describing the fallback pipeline and noting it 'Replaces 4–6 sequential calls'. The inclusion of example query phrasings makes the 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.' It also describes two distinct paths (company-financial vs. any other factual claim) and instructs callers on interpreting verdict values. However, it does not explicitly name sibling tools to avoid or contrast with, so it falls short of a 5 on explicit when-not-to-use guidance.

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