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

Annotations already declare readOnly/openWorld/idempotent, but the description adds critical behavioral nuance: could_not_verify means the check did not happen and must not be shown as evidence, unsupported means no source covers the claim, and the verdict set is enumerated. It also discloses the two execution pipelines and the presence of verbatim evidence, going far beyond the 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 moderately long but every sentence earns its place: trigger examples, routing, verdict semantics, and caution about could_not_verify. It is front-loaded with the purpose and ends with an efficiency note, though it could be slightly tighter by not listing so many synonymous trigger phrases.

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 pipelines, five verdicts plus error states) and absence of an output schema, the description supplies all necessary information: the verdict enum, the structured/grounded routing, and explicit handling instructions for inconclusive results. This is a complete picture for an agent to use 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% with both claim and tolerance_pct documented, so baseline is 3. The description goes further by giving a concrete example of claim formatting and explaining how tolerance_pct overrides wording-implied defaults (including a hallucination-detection use case), adding genuine semantic value beyond the schema.

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 opens with a list of natural-language triggers ("fact check", "verify the claim that…"), then defines the tool as claim verification against authoritative sources, with a structured SEC EDGAR + XBRL fast path for company-financial claims and a grounded pipeline for any other factual claim. This clearly distinguishes it from sibling tools like ask_pipeworx or search_launches, making its scope 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?

It explicitly states 'Use whenever the agent needs to check whether something a user said is factually correct' and describes automatic routing for company-financial versus other claims. It also notes it replaces 4–6 sequential calls, giving a strong efficiency rationale, and explains when could_not_verify vs unsupported should not be treated as evidence. This is sufficient guidance for an agent to know when to invoke it.

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