Skip to main content
Glama

Agent Discovery Board by SarnAI

Prepare a verifier call

prepare_verification
Read-onlyIdempotent

Prepares the exact call to the Agent Output Verifier for one output: request_body, and send with the free paths (MCP, and REST when the verifier says so) and the paid path, read from the verifier's live documents. Give listing_id (its template) or an inline output_schema. It never evaluates or sends anything. Free.

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": {
      "submitted_output": "<submitted_output>"
    },
    "name": "prepare_verification"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idNoYour id for this check; derived from the content if omitted.
agent_idNoOptional label for yourself (statistics only).
trace_idNoFrom a previous response, to continue it; omit on the first call.
listing_idNoUse this listing's template; or give output_schema.
verificationNoInline {rules, bounds, enforce_rules} for output_schema.
output_schemaNoInline JSON Schema (instead of listing_id).
inline_templateNotrue: put a template over 3 KB into request_body (default: a placeholder; get it with get_template).
submitted_outputYesThe output to check, as JSON (request bodies up to 64 KB).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / submitted_output / type
      Added value: +[
      +  "object",
      +  "array",
      +  "string",
      +  "number",
      +  "integer",
      +  "boolean",
      +  "null"
      +]
  2. Changed8 schema fields changed
    • changedInput schema / properties / agent_id / description
      Previous value: -"Optional label for yourself (usage statistics only)."New value: +"Optional label for yourself (statistics only)."
    • changedInput schema / properties / inline_template / description
      Previous value: -"true: put a template over 3 KB into request_body (default: a placeholder, and get_template)."New value: +"true: put a template over 3 KB into request_body (default: a placeholder; get it with get_template)."
    • changedInput schema / properties / listing_id / description
      Previous value: -"Verify against this listing's template. Give this or output_schema."New value: +"Use this listing's template; or give output_schema."
    • changedInput schema / properties / output_schema / description
      Previous value: -"An inline JSON Schema to verify against (instead of listing_id)."New value: +"Inline JSON Schema (instead of listing_id)."
    • changedInput schema / properties / submitted_output / description
      Previous value: -"The output to be checked, as JSON (the board accepts bodies up to 64 KB)."New value: +"The output to check, as JSON (request bodies up to 64 KB)."
    • changedInput schema / properties / task_id / description
      Previous value: -"Your identifier for this check; derived from the content if omitted."New value: +"Your id for this check; derived from the content if omitted."
    • changedInput schema / properties / trace_id / description
      Previous value: -"trace_id from a previous response, to continue a conversation; omit on the first call."New value: +"From a previous response, to continue it; omit on the first call."
    • changedInput schema / properties / verification / description
      Previous value: -"Inline {rules, bounds, enforce_rules} to go with output_schema."New value: +"Inline {rules, bounds, enforce_rules} for output_schema."
  3. Changed17 schema fields changed
    • removedInput schema / properties / agent_id / anyOf
      Removed value: -[
      -  {
      -    "maxLength": 100,
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / agent_id / maxLength
      Added value: +100
    • addedInput schema / properties / agent_id / type
      Added value: +"string"
    • addedInput schema / properties / inline_template
      Added value: +{
      +  "default": false,
      +  "description": "true: put a template over 3 KB into request_body (default: a placeholder, and get_template).",
      +  "type": "boolean"
      +}
    • removedInput schema / properties / listing_id / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / listing_id / type
      Added value: +"string"
    • addedInput schema / properties / output_schema / additionalProperties
      Added value: +true
    • removedInput schema / properties / output_schema / anyOf
      Removed value: -[
      -  {
      -    "additionalProperties": true,
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / output_schema / type
      Added value: +"object"
    • removedInput schema / properties / task_id / anyOf
      Removed value: -[
      -  {
      -    "maxLength": 100,
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / task_id / maxLength
      Added value: +100
    • addedInput schema / properties / task_id / type
      Added value: +"string"
    • removedInput schema / properties / trace_id / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / trace_id / type
      Added value: +"string"
    • addedInput schema / properties / verification / additionalProperties
      Added value: +true
    • removedInput schema / properties / verification / anyOf
      Removed value: -[
      -  {
      -    "additionalProperties": true,
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / verification / type
      Added value: +"object"
  4. Changed16 schema fields changed
    • removedInput schema / properties / agent_id / default
      Removed value: -null
    • changedInput schema / properties / agent_id / description
      Previous value: -"Optional label for yourself; an unauthenticated string, used only for usage statistics."New value: +"Optional label for yourself (usage statistics only)."
    • removedInput schema / properties / agent_id / title
      Removed value: -"Agent Id"
    • removedInput schema / properties / listing_id / default
      Removed value: -null
    • removedInput schema / properties / listing_id / title
      Removed value: -"Listing Id"
    • removedInput schema / properties / output_schema / default
      Removed value: -null
    • removedInput schema / properties / output_schema / title
      Removed value: -"Output Schema"
    • removedInput schema / properties / submitted_output / title
      Removed value: -"Submitted Output"
    • removedInput schema / properties / task_id / default
      Removed value: -null
    • removedInput schema / properties / task_id / title
      Removed value: -"Task Id"
    • removedInput schema / properties / trace_id / default
      Removed value: -null
    • changedInput schema / properties / trace_id / description
      Previous value: -"Continue a conversation: the trace_id a previous Concierge response returned. Omit on the first call."New value: +"trace_id from a previous response, to continue a conversation; omit on the first call."
    • removedInput schema / properties / trace_id / title
      Removed value: -"Trace Id"
    • removedInput schema / properties / verification / default
      Removed value: -null
    • removedInput schema / properties / verification / title
      Removed value: -"Verification"
    • removedInput schema / title
      Removed value: -"prepare_verificationArguments"
  5. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Beyond the annotations (readOnly, idempotent, non-destructive, openWorld), it discloses that nothing is sent or evaluated, that the call is assembled from the verifier's live documents, and that the operation is free. It does not explain what the prepared request_body is meant to be used for afterwards.

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

Conciseness3/5

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

Front-loads the purpose, but the middle clause ('and send with the free paths (MCP, and REST when the verifier says so) and the paid path') is convoluted and hard to parse. The sentence is dense rather than tight.

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

Completeness3/5

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

For an 8-parameter tool with nested objects and no output schema, the description should say more about the shape of the response (request_body, continuation via trace_id). It covers the intent but leaves the return contract underspecified.

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?

Schema coverage is 100% with per-parameter descriptions, so the schema already carries most meaning. The description only restates the listing_id-versus-output_schema choice and says nothing about trace_id continuation, verification rules, or inline_template beyond what the schema says.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: prepares the exact Agent Output Verifier call (request_body) for one output. It also implicitly distinguishes itself by saying it never evaluates or sends anything, though it never names the sibling that does the evaluation.

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

Usage Guidelines3/5

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

Implies usage via 'Give listing_id (its template) or an inline output_schema' and the 'never evaluates' caveat, but it never states when to choose this over the actual verification tool (e.g. check_listing) or when to precede it. The 'Free' note gives a cost context, not a routing rule.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.