Skip to main content
Glama

veritap

by dev.veritap

Confirm a listing or seller is real before spending money

confirm_before_purchase
Read-onlyIdempotent

Check whether a listing, item, or business can be corroborated before an agent commits money. Free, read-only, no side effects.

Use before any irreversible spend where the counterparty or the goods have only been seen online. Returns what can be corroborated from sources, what cannot, and — when it cannot — whether you could settle it yourself and how to proceed if not.

Every request is recorded and analysed in aggregate to decide what gets supported next (https://veritap.dev/terms).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
deadlineNoISO8601. When the answer stops being useful.
locationNoWhere the fact must be checked.
claim_typeNoOptional. A claim type id from the published catalog, if you know it.
callback_urlNoOptional. If this claim is not supported yet, POST here when it becomes supported. Otherwise you are told on your next call.
task_contextNoThe wider task this step belongs to.
cost_if_wrongNoWhat happens to your task if this fact is wrong: "blocks_task", "degrades_answer", or "cosmetic".
claim_descriptionYesFree text. The real-world fact you need settled. Required.
downstream_actionNoWhat you will do with the answer once you have it.
budget_ceiling_usdNoMost you would pay for this answer. Directly drives what gets built next.

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that the tool is free, read-only, with no side effects, returns what can and cannot be corroborated, and that every request is recorded and used for aggregate feature decisions. This goes beyond the annotations and gives the agent a clear picture of the tool's behavior, though the 'no side effects' phrasing is slightly at odds with the recording note.

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, front-loaded with purpose and safety, with no filler. The privacy/analytics note is useful and the return behavior is summarized in one sentence. Every sentence earns its place.

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 tool has 9 parameters and no output schema, but the description covers the when, the what, and the shape of the return value (corroborated vs. not, self-settle guidance). The rich schema handles the parameters. It could have named alternative tools for non-purchase checks, but it is sufficiently complete for an agent to invoke correctly.

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?

The input schema covers 100% of the 9 parameters with detailed descriptions, so the schema does the heavy lifting. The description adds no per-parameter syntax or format details, but this is not necessary at this coverage level; it does indirectly reference the unsupported-claim and callback workflow in prose. The baseline of 3 is appropriate.

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?

The description uses 'Check whether a listing, item, or business can be corroborated before an agent commits money,' which names a specific action (corroborate/check), a specific resource class (listing/item/business/seller), and the monetary context. This clearly differentiates it from siblings like check_physical_condition or plan_verification.

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?

It explicitly instructs to use it 'before any irreversible spend where the counterparty or the goods have only been seen online,' giving a concrete trigger condition. It does not compare to sibling tools by name, but the spending context is enough for an agent to select it over general-purpose alternatives.

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

All veritap 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

A3.8/5.0
Disambiguation2/5

Several tools overlap significantly. check_before_relying and check_feasibility both check whether a fact can be corroborated, with minimal distinction. confirm_before_purchase is a purchase-specific variant, and plan_verification/triage_unknowns both handle planning-stage uncertainty. Agents would struggle to pick the right one.

Naming Consistency2/5

The verb set is inconsistent: check, confirm, plan, triage. Some objects are nouns (feasibility, physical_condition, verification, unknowns) while others are adverbial phrases (before_relying, before_purchase). No uniform verb_noun pattern.

Tool Count4/5

Six tools is within a reasonable range for the verification domain. The count is not excessive, though some tools could be consolidated to reduce redundancy.

Completeness4/5

The set covers general verification, feasibility, physical condition, purchase decisions, plan mapping, and uncertainty triage. Minor gaps exist (e.g., no explicit identity/authenticity check), but the coverage is largely sufficient for the stated purpose.

Resources