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

Beyond the readOnlyHint and idempotentHint annotations, the description adds critical behavioral detail: the distinction between 'could_not_verify' (meaning the check didn't happen and must not be treated as evidence) and 'unsupported' (no source covers it). It also discloses the routing logic to SEC EDGAR/XBRL vs. grounded pipeline and the return structure (verdict, actual value, citation, reasoning). This is exactly the kind of transparency needed for correct invocation.

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 densely informative but well-structured: examples → purpose → routing → output → caller warnings → efficiency note. Every sentence adds value, and the key 'IMPORTANT for callers' caveat is clearly flagged. Despite its length, it avoids redundancy and remains scannable.

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?

With no output schema, the description fully enumerates the possible verdicts and explains the error case ('could_not_verify' with verification_error). It also covers the two main input paths, mentions citations, and clarifies unsupported. For a tool with this complexity, the description provides complete operational context, leaving little ambiguity.

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 echoes the schema's explanation of tolerance_pct ('Overrides the tolerance implied by the claim wording') and adds context about 'exact percent-delta math,' but this is marginal. It does not introduce new parameter-level meaning beyond what the schema already provides, so a baseline 3 is appropriate.

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 natural-language phrasings ('Is it true that…', 'fact check') and states clearly that the tool performs 'natural-language claim verification against authoritative sources.' It distinguishes itself from siblings by detailing the SEC EDGAR + XBRL fast path for financial claims and the grounded pipeline for all other claims, making it unique among the sibling tools.

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,' giving a clear trigger condition. It also notes that it 'replaces 4–6 sequential calls,' signaling that it should be chosen over chaining multiple simpler tools. Internal routing rules (company-financial vs. other claims) further guide when specific paths are taken.

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