Skip to main content
Glama
ActaLumen

@actalumen/mcp-server

Official
by ActaLumen

start_verification

Run compliance verification on a document by providing a documentId and either a templateId or custom criteria. Returns a jobId to poll for completion.

Instructions

Run compliance verification on a document against a template (or ad-hoc criteria). Returns a jobId; the job runs async — poll get_verification until status is 'completed'. Requires the API key to have the 'verify' scope.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
documentIdYesDocument to verify. Must be READY (see get_document).
templateIdNoTemplate ID from list_templates. Either templateId or criteria is required.
criteriaNoAd-hoc criteria list, used when no template fits. Either templateId or criteria is required.

Implementation Reference

  • The handler function that executes the start_verification tool logic — sends a POST to /v1/reports with the input payload via the API client.
    export const startVerification = defineTool({
      name: "start_verification",
      description:
        "Run compliance verification on a document against a template (or ad-hoc criteria). Returns a jobId; the job runs async — poll get_verification until status is 'completed'. Requires the API key to have the 'verify' scope.",
      inputSchema: Input,
      handler: async (input, { client }) => client.post("/v1/reports", input),
  • Input schema defining documentId (string, required), templateId (number, optional), and criteria (array of {id, text}, optional) with a refinement requiring either templateId or a non-empty criteria array.
    const Input = z
      .object({
        documentId: z.string().describe("Document to verify. Must be READY (see get_document)."),
        templateId: z
          .number()
          .int()
          .optional()
          .describe("Template ID from list_templates. Either templateId or criteria is required."),
        criteria: z
          .array(z.object({ id: z.string(), text: z.string() }))
          .optional()
          .describe("Ad-hoc criteria list, used when no template fits. Either templateId or criteria is required."),
      })
      .refine((v) => v.templateId !== undefined || (v.criteria && v.criteria.length > 0), {
        message: "Provide either templateId or a non-empty criteria array.",
      });
  • Registration: startVerification is imported from './start_verification.js' and included in the tools array that exports all ToolDefs.
    import { startVerification } from "./start_verification.js";
    import { getVerification } from "./get_verification.js";
    import { chatWithDocument } from "./chat_with_document.js";
    import { getUsage } from "./get_usage.js";
    
    export const tools: ToolDef[] = [
      uploadDocument,
      getDocument,
      listDocuments,
      listTemplates,
      startVerification,
      getVerification,
      chatWithDocument,
      getUsage,
    ];
  • startVerification is included in the exported tools array (position 5 out of 8 tools).
      startVerification,
      getVerification,
      chatWithDocument,
      getUsage,
    ];
  • The defineTool helper function used to create the tool definition with type-safe input schema and handler.
    export function defineTool<Input extends z.ZodTypeAny>(t: {
      name: string;
      description: string;
      inputSchema: Input;
      handler: (input: z.infer<Input>, ctx: ToolContext) => Promise<unknown>;
    }): ToolDef {
      return t as unknown as ToolDef;
    }
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses async behavior, polling requirement, and auth scope ('verify'). It does not mention potential side effects or prerequisites beyond document readiness, which is in the schema.

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?

The description is two sentences: first states the action, second explains the result and follow-up, third notes the scope requirement. No unnecessary words, front-loaded, and well-structured.

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?

Given the tool's complexity (async, 3 params, no output schema), the description covers the main points: purpose, result (jobId), polling method, and auth. It could mention that the document must be READY (though schema does) or note the lack of output schema, but overall sufficient.

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 has 100% coverage with clear descriptions for each parameter (e.g., documentId must be READY). The description adds no further parameter-specific details beyond the schema, meeting the baseline for high coverage.

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 clearly states the verb 'Run compliance verification' on a document, specifies both template and ad-hoc criteria, and distinguishes from siblings like get_verification (polling) and upload_document.

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?

The description explains that the job runs asynchronously and must be polled via get_verification, and mentions the required API scope. However, it does not explicitly state when not to use this tool or compare with siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ActaLumen/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server