Verify AI-generated answers against real sources before anyone acts on them. Returns a trust signal plus a permanent doc number anyone can verify free at oathlayer.com/verify. Works on any AI model.
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools, so disambiguation is perfect.
The single tool name 'verify_output' follows a clear verb_noun pattern with no inconsistencies.
Having one tool is borderline; it may be appropriate for a narrow purpose but feels thin compared to typical well-scoped servers that have 3-15 tools.
The tool only allows submission of a question, but lacks retrieval or management of the returned doc reference, creating significant gaps for tracking or reusing verification results.
Submit a question to Oathlayer for verification. Returns whether the answer is approved, unverified, reflects multiple perspectives, is too complex to verify, or needs clarification. Also returns a permanent doc reference number.
| Name | Required | Description | Default |
|---|---|---|---|
| apiKey | Yes | Your Oathlayer API key from your dashboard at oathlayer.com. | |
| question | Yes | The question or statement you want Oathlayer to verify. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully convey behavioral traits. It mentions output types but fails to disclose potential side effects, rate limits, error handling, or any destructive actions. The description is adequate but not comprehensive for a tool without annotations.
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 two sentences long, front-loaded with the action and immediate outcome, followed by specific return details. Every sentence adds value with no redundancy.
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 no output schema, the description adequately lists possible return statuses and a doc reference number, but lacks details on the output structure (e.g., JSON fields) and error scenarios. It is mostly complete for a simple tool.
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 coverage is 100%, so the baseline is 3. The description does not add meaning beyond the schema; it references the 'question' parameter indirectly but does not elaborate on 'apiKey'. The schema descriptions are already self-explanatory.
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 clearly states the tool submits a question for verification and lists possible return statuses (approved, unverified, etc.) and a permanent doc reference number. It uses a specific verb ('submit') and resource ('question'), distinguishing it from any potential alternative tools, though none are provided.
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?
The description implies the tool is used for verifying statements, but provides no explicit guidance on when to use it versus alternatives, when not to use it, or prerequisites beyond the apiKey. With no sibling tools, the absence of such guidance is less critical but still leaves gaps.
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_output
Add one secure layer between your agents and this server.