Tru8 Evidence Research

tru8_check

Evidence research for a factual claim or article URL.

Submit a claim as text or paste an article URL. URLs are auto-detected
and trigger article mode: the pipeline extracts claims from the page
and auto-selects up to 5 for evidence research.

Tiers (in fallback order):
- lookup    (~£0.02, instant) — cached prior analysis
- consensus (~£0.03, instant) — cross-user aggregate landscape (k≥3 checks)
- quick     (~£0.07, ~15s) — web search + heuristic classification
- full      (~£0.15, ~60-90s) — web + specialist APIs, LLM classification, coverage recovery

Charges based on tier actually executed, not tier requested.
Identical calls within ten minutes return the same check, so a
transport retry never runs — or charges — twice.
Set max_tier to control maximum spend per call.

Output structure:
- claims[].claimMap.elements[] — verifiable sub-claims with state
  (supported/disputed/unresolved)
- claims[].claimMap.elements[].evidenceRefs[] — evidence mapped to elements
  with relationship (supports/challenges/context) and reasoning
- claims[].evidence[] — sources classified by tier (primary/reporting/
  commentary) and type (data/official/news/analysis/opinion/academic)
- claims[].claimMap.orientation — mechanical summary from element states
- _meta — execution metadata: executedTier, chargedPence, limitations

A run that has not finished after several minutes returns
{checkId, status, chargedPence, message} instead of the result: fetch it
later with tru8_get_result (free). A run that FAILS raises an error and is
not charged.

Per-argument guidance lives on the parameters themselves (see the
Annotated/Field declarations above), which is where a client can actually
read it — a docstring "Args:" block never reaches the tool's inputSchema.

Input Schema

Name	Required	Description	Default
`claim`	Yes	A factual claim ("The Earth's average temperature rose 1.1°C since 1880") or an article URL (https://example.com/article). URLs are auto-detected and the pipeline extracts claims from the page content.
`compact`	No	If true, strip the full evidence arrays and computed analytics from the response, leaving claims and claim maps. Smaller payload for agents that only need orientation.
`max_tier`	No	Maximum tier to attempt — "lookup", "consensus", "quick" or "full" (default). A CEILING, not a floor: cached and consensus hits still return instantly at their own lower price, so the default costs ~£0.15 only for claims never researched before. Set "quick" to cap spend at ~£0.07, accepting web-search-only sourcing and heuristic classification (see _meta.limitations).	full
`max_age_hours`	No	Skip cache hits older than this many hours. Stale lookup hits are discarded and the pipeline re-runs at the next tier up to max_tier. 0 means never serve a cached result.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedAug 10, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the annotations, which only declare readOnly=false, openWorld=true, idempotent=false, destructive=false. The description discloses pricing per tier, that billing follows the tier actually executed rather than requested, a 10-minute dedupe window that prevents double charging on retries, that failures raise errors and are not charged, and that slow runs return a partial {checkId, status, chargedPence, message} payload. These are non-obvious cost and side-effect behaviours an agent must know before invoking.

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

Conciseness4/5

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

Front-loaded purpose, then cleanly sectioned tiers and output structure — appropriate for a tool with this much pricing and fallback complexity. Minor waste: the closing paragraph about docstrings not reaching inputSchema is meta-commentary aimed at tool authors, not at an agent selecting the tool, and pricing is restated between the tier table and the max_tier narrative.

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

Completeness5/5

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

Despite an output schema existing, the description's summary of the nested return shape (claims[].claimMap.elements[], evidenceRefs[], evidence[], _meta) is genuinely useful orientation for a deeply nested payload. Failure modes, partial-return handling, billing semantics and cache staleness are all covered, leaving no obvious gap for correct invocation.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic content: it frames max_tier as a CEILING not a floor via the tier fallback table, and explains that charges depend on the executed tier. It also explicitly notes that per-argument guidance lives in the schema rather than a docstring, which is a useful pointer.

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?

Opens with a specific verb+resource combination ('Evidence research for a factual claim or article URL') and immediately clarifies the two accepted input modes. It also names tru8_get_result as the retrieval path for unfinished runs, so an agent can distinguish it from its siblings without opening their schemas.

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

Usage Guidelines5/5

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

Explicit conditions: submit a claim as text or a URL (auto-detected, triggers article mode with up to 5 extracted claims), set max_tier to cap spend, and use tru8_get_result (free) if the run returns a pending object. The tier fallback order with costs and latencies tells the agent exactly what behaviour to expect at each spend level.

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

All Tru8 Evidence Research tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.