Skip to main content
Glama

Fidenta Verify

by ai.noevant

verify_claims

Idempotent

Fact-check text against live web evidence from two independent retrievers, then have a model from a different lab audit the verdict. Returns per-claim verdicts: SUPPORTED, CONTRADICTED, UNSUPPORTED (searched and found nothing — not the same as false), or UNVERIFIABLE (opinion or prediction). Use before relying on a factual claim, or to check your own draft answer before sending it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoA public http(s) link to an article or web page. We fetch it, extract the readable text and verify the claims in it. Use this when the user gives you a link instead of text — you do not need to fetch the page yourself. Pages behind a login or paywall cannot be read; ask for the text instead.
textNoThe text to verify. A single claim or a full answer containing several. May also be a bare link, e.g. 'verify https://example.com/article'.
forceNoRe-check even if a recent saved result exists.
confirmNoRequired to proceed when the text contains more than 3 checkable claims. Call estimate_claims first, tell the user the claim count and credit cost, then call again with confirm true once they agree.
max_claimsNoHard cap on how many claims to verify, and therefore on how many credits this call can spend. Use it to bound cost on a long document.

TDQS

A4.2/5.0
Behavior4/5

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

The description adds the unique two-retriever and cross-lab audit process, plus the semantic distinction between UNSUPPORTED and false, which is not captured by the annotations. Annotations already provide readOnly/openWorld/idempotent hints, but the description enriches understanding of the tool's internal operation and verdict semantics. No contradiction found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, with the key information front-loaded: the core action, the verdict types, and the recommended use cases. Every sentence carries unique information—no filler or tautology.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the tool's purpose, return values (per-claim verdicts), and the meaning of each verdict, which is sufficient despite no output schema. Combined with the rich parameter descriptions and annotations, the tool is fully comprehensible for invocation. Minor gap: the credit-cost and confirmation flow are only mentioned in the confirm parameter description, not in the main description, but this is adequately covered by the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover all five parameters with high detail (100% coverage), including url fetching behavior, confirm's cost flow, and max_claims as a cap. The description itself adds no parameter-specific guidance, so it earns the baseline 3 for schema-heavy tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description opens with 'Fact-check text against live web evidence from two independent retrievers, then have a model from a different lab audit the verdict.' This clearly names the action, resource, and distinctive process, distinguishing it from siblings like estimate_claims. The per-claim verdict list further clarifies scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states 'Use before relying on a factual claim, or to check your own draft answer before sending it,' providing concrete trigger conditions. It does not explicitly name alternatives or exclusions, though siblings like estimate_claims have distinct roles that are referenced in the schema's confirm parameter.

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

All Fidenta Verify toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool serves a distinct function: usage monitoring, cost estimation, historical lookup, credit purchase, and actual verification. There is no semantic overlap between the tool purposes.

Naming Consistency4/5

Four tools follow a verb_noun pattern (check_usage, estimate_claims, recall_claim, verify_claims), but top_up is a phrasal verb deviating from this pattern. Still, all names are imperative and consistently lowercase with underscores.

Tool Count5/5

Five tools is a well-scoped set for a credit-based verification service. Each tool earns its place, covering the essential actions without redundancy or bloat.

Completeness4/5

The set covers the full verification workflow: estimate cost, verify claims, recall prior verifications, check usage, and top up credits. A minor gap is that recall_claim only checks whether a claim was verified, not retrieving the previous verdict, but the core lifecycle is complete.

Resources