Oathlayer is an independent check on AI answers. It checks each answer against independent sources, gives it a clear verification tag, and records it with a permanent doc number that anyone can look up free at oathlayer.com/verify. It reports what happened; it does not judge right or wrong. Works on any topic and with any AI model.
Tool: verify_output. Connect at https://mcp.oathlayer.com.
The Five Pillars of Trust: Verification Successful - Oath Approved; Verification Threshold Not Met; Various Perspectives Apply; Complex Question - Threshold Reserved; Clarity Needed to Continue.
Citation Checks: paste a case citation and Oathlayer checks it against official court sources. Each citation gets a short tag: Confirmed, Unofficial, Mismatched or Not found. If trusted sources report a case was overruled, it says Reported overruled. It checks the citation only, not whether the case supports your argument.
Also available as Oathlayer Chat (no programming needed) and an API (oathlayer.com/docs).
Free trial: 5 free verifications, no card needed (oathlayer.com/signup). Then pay as you go: one credit per check, credits valid 12 months, no subscriptions.
Scored across 1 tool
There is only one tool, so there is no possibility of selecting the wrong tool. Its purpose—verifying an AI answer against independent sources—is clearly stated and distinct.
The single tool name, verify_output, follows a clear verb_noun convention. With only one tool, there is no inconsistency to assess.
A single tool is arguably sufficient for a one-shot verification service, but it is on the thin side for a server with several described result states and citation modes. No separate tools exist for batch checks, history, or status lookup.
The tool covers the core end-to-end verification workflow, including the answer, state, message, color, and permanent doc number. Minor gaps exist around batch verification or retrieving past verification records, but the primary operation is complete.
Verify an AI answer against real sources before anyone acts on it. Send a question; Oathlayer answers it, checks the answer against independent sources, and returns the answer, a state, a plain-language message (the tag), a color, and a permanent doc number anyone can verify free at oathlayer.com/verify. Tags: Verification Successful - Oath Approved (green); Verification Threshold Not Met (blue); Various Perspectives Apply (purple); Complex Question - Threshold Reserved; Clarity Needed to Continue (pink). Legal citations also get a citation tag: confirmed on official sources (green), found only on unofficial sites (blue), mismatched with the correct citation shown (coral), or not found in available sources (golden brown). Citation answers also include a short label: Confirmed, Unofficial, Mismatched or Not found. Oathlayer reports what happened; it does not judge right or wrong. Works on any topic and with any AI model. Costs one credit per completed check; errors and wrong keys cost nothing. Requires an API key from oathlayer.com.
| Name | Required | Description | Default |
|---|---|---|---|
| apiKey | Yes | Your Oathlayer API key from oathlayer.com. Each completed check uses one credit. | |
| question | Yes | The question to verify, in plain words (for a legal citation, include the full case name and citation). Spanish questions are supported. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden and does so well. It discloses the verification process, the returned fields, tag meanings and colors, citation-specific tags and labels, billing behavior (one credit per completed check, errors and wrong keys free), API key requirement, and the important boundary that Oathlayer reports findings without judging right or wrong.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose and then organizes return states, citation tags, billing, and requirements. It is lengthy, but the density is justified because there is no output schema and the agent needs the tag/color semantics to interpret results.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and an output schema, the description is complete enough for correct invocation and interpretation. It covers inputs, output fields, tag semantics, citation-specific results, cost behavior, and authentication requirements.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both parameters are already documented in the schema. The description adds context around sending a question and legal-citation verification, but it does not materially extend the parameter semantics beyond what the schema already states.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: verify an AI answer against real sources. It explains the full workflow—send a question, Oathlayer answers and checks it independently, then returns a verification result—with enough detail that an agent can distinguish this as a source-verification tool rather than a general Q&A tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives clear usage context: use it before anyone acts on an AI answer, it works on any topic and any model, and each completed check costs one credit. It does not name explicit exclusions or alternatives, but there are no sibling tools, so the guidance is largely complete for its scope.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
verify_output2 fields changedInput schema / properties / apiKey / descriptionPrevious value: -"Your Oathlayer API key from your dashboard at oathlayer.com."New value: +"Your Oathlayer API key from oathlayer.com. Each completed check uses one credit."Input schema / properties / question / descriptionPrevious value: -"The question or statement you want Oathlayer to verify."New value: +"The question to verify, in plain words (for a legal citation, include the full case name and citation). Spanish questions are supported."verify_outputVerify legal citations, case treatment, quotes and whole briefs against 10.7M U.S. opinions
Resolve, search and verify legal citations against the official sources, with provenance.
Verify legal citations, check case validity and quotes, and research US law with cited answers.
Verifies legal citations vs primary sources: existence, quote match, proposition support.
Add one secure layer between your agents and this server.
