MethodPublished

Tool Capability Verification Method

Tool profile should expose evidence state beside claim instead of collapsing every source into one confidence score.

Capability claim needs source, source type, verification date, and status. This method avoids treating vendor documentation and independent observation as equivalent.

Evidence classes

ClassMeaningAllowed wording
OfficialVendor or publisher documents capability"Documentation says..."
ObservedReproducible dated test produced result"Our test produced..."
InferredEvidence supports conclusion indirectly"Evidence suggests..."
StaleSource or test exceeds refresh window"Last verified..."
ContradictedSources or tests disagreeDescribe conflict
UnknownEvidence cannot answer questionState unknown

Claim record

statement: product exports editable email HTML
source_url: https://example.com/docs/export
source_type: official-documentation
verified_at: 2026-08-10
status: vendor-documented
reviewer: contributor-id

Observed test adds input, account tier, product version, environment, expected result, output, and repetition count.

Freshness

Refresh interval follows volatility. Pricing and model assignment change faster than company founding date. Do not update visible date unless evidence or wording changed.

Conflicts

When official pages disagree, show conflict. Do not silently select more favorable source. When observed test contradicts documentation, preserve both and describe test boundary.

Affiliations

Every profile records submitter and reviewer relationship to subject. Affiliation does not disqualify contribution, but it must remain visible and should not control final comparative conclusion.

Output

Method produces inspectable claim ledger. Readers and agents can filter official, observed, inferred, stale, contradicted, and unknown statements without relying on opaque editorial score.

Sources

Evidence used on this page

  1. NIST AI Risk Management Framework
  2. Google people-first content guidance