Lenz Fact-Check

Choose which claims to check

select_claims

Idempotent

Run a deep check on the claims the user picks when a text holds several (this resolves a needs_input verification).

When verify_claim or get_verification returns status: needs_input with reason multi_claim, call this with that task_id and a claims list of one or more of the offered claim texts, exactly as listed. Each selected claim starts its own deep verification. With ONE claim selected this waits for the check and returns its result like get_verification (with the new task_id); with several it returns their new task_ids to pass to get_verification.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task_id": "<task_id>",
      "claims": "<claims>"
    },
    "name": "select_claims"
  }
}

Input Schema

Name	Required	Description	Default
`claims`	Yes	One or more of the exact claim texts offered by verify_claim or get_verification (its `claims`). Each selected claim starts its own deep verification.
`task_id`	Yes	The task_id of the needs_input verification being resolved (from the verify_claim or get_verification response).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 22, 2026

changedInput schema / properties / claims / description

Previous value: -"One or more of the exact claim texts offered by get_verification (its `claims`). Each selected claim starts its own deep verification."New value: +"One or more of the exact claim texts offered by verify_claim or get_verification (its `claims`). Each selected claim starts its own deep verification."

changedInput schema / properties / task_id / description

Previous value: -"The task_id of the needs_input verification being resolved (from the get_verification response)."New value: +"The task_id of the needs_input verification being resolved (from the verify_claim or get_verification response)."

First observedOct 6, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only declare generic hints (readOnlyHint false, openWorldHint true, idempotentHint true), so the description carries real weight and does: it discloses that each selected claim spawns its own deep verification, that one claim blocks and returns a result while several return new task_ids, and that the call must use exact claim texts. This is genuine behavioral context beyond the structured fields.

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?

Two sentences, front-loaded with the purpose and trigger in the first, then the mechanics and return-shape branching in the second. Nothing is wasted and the branch on claim count is easy to act on.

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?

An output schema exists, so return values needn't be described, yet the definition still sketches the two return shapes (single-claim result vs. multiple task_ids), which is what an agent needs to decide its next call. For a two-parameter tool with full schema coverage, nothing important is missing.

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 meaning: task_id must come from the needs_input response, and claims must be exact texts drawn from the offered list rather than free-form strings. The exception is that it doesn't say what happens when a supplied text doesn't match an offered claim.

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?

States a specific verb and resource ("run a deep check on the claims the user picks") plus the qualifying condition ("when a text holds several"). It also names its role in the workflow, resolving a needs_input verification, which separates it from verify_claim and get_verification.

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?

Gives an explicit trigger: call this when verify_claim or get_verification returns status: needs_input with reason multi_claim. It also states the input source (the offered claim texts, exactly as listed) and notes the distinction from verify_claim, leaving no ambiguity about when this tool applies.

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

All Lenz Fact-Check 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.