Skip to main content
Glama

Agent Discovery Board by SarnAI

Build a verification template

build_template
Read-onlyIdempotent

Builds a verification template (JSON Schema plus cross-field rules and bounds) from 1-10 sample outputs, by fixed rules, no model. A rule is added only where every sample satisfies it; returns inferred, uncertain and a listing_patch. Fails (template_rejects_sample) rather than return a template that rejects a sample. Stores nothing. Free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "build_template"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoOptional schema title.
samplesNo1-10 example outputs as JSON, at most 32 KB in all; varied samples show which fields are optional.
agent_idNoOptional label for yourself (statistics only).
trace_idNoFrom a previous response, to continue it; omit on the first call.
expectationsNoWhat samples cannot show: required fields, unique array fields, ranges.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / expectations / type
      Added value: +"object"
  2. Changed5 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 / expectations / description
      Previous value: -"Things you know that samples cannot show: required fields, unique array fields, numeric ranges."New value: +"What samples cannot show: required fields, unique array fields, ranges."
    • changedInput schema / properties / name / description
      Previous value: -"Optional title for the schema."New value: +"Optional schema title."
    • changedInput schema / properties / samples / description
      Previous value: -"One to 10 example outputs of your service, as JSON (at most 32 KB in all). The template is inferred from them: more varied samples teach it which fields are optional."New value: +"1-10 example outputs as JSON, at most 32 KB in all; varied samples show which fields are optional."
    • 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."
  3. Changed17 schema fields changed
    • removedInput schema / $defs / Range / properties / max / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / $defs / Range / properties / max / type
      Added value: +"number"
    • removedInput schema / $defs / Range / properties / min / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / $defs / Range / properties / min / type
      Added value: +"number"
    • 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 / expectations / $ref
      Added value: +"#/$defs/Expectations"
    • removedInput schema / properties / expectations / anyOf
      Removed value: -[
      -  {
      -    "$ref": "#/$defs/Expectations"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / properties / name / anyOf
      Removed value: -[
      -  {
      -    "maxLength": 100,
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / name / maxLength
      Added value: +100
    • addedInput schema / properties / name / type
      Added value: +"string"
    • removedInput schema / properties / samples / anyOf
      Removed value: -[
      -  {
      -    "items": {},
      -    "type": "array"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / samples / items
      Added value: +{}
    • addedInput schema / properties / samples / type
      Added value: +"array"
    • removedInput schema / properties / trace_id / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / trace_id / type
      Added value: +"string"
  4. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description still adds real value beyond them: deterministic 'fixed rules, no model', fail-fast with 'template_rejects_sample' rather than emitting a bad template, 'Stores nothing', and 'Free'. It does not explain what 'inferred', 'uncertain' or 'listing_patch' actually mean in the response, which is the remaining behavioral gap.

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

Conciseness4/5

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

Front-loaded with the core action and heavily compressed; almost every clause carries information (rules, failure mode, storage, cost). However, the telegraphic fragments ('returns inferred, uncertain and a listing_patch') read as jargon and could be clearer without adding length.

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?

With no output schema, the description takes on return-value disclosure and does partly: it names the failure code and several response fields. For a read-only builder with a 5-parameter nested schema, the main omissions are the meaning of 'uncertain'/'listing_patch' and how trace_id continuation behaves across calls.

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 description coverage is 100%, so the schema already documents name, samples, agent_id, trace_id and expectations, including limits like 32 KB and 1-10 samples. The description largely repeats what the schema says ('from 1-10 sample outputs') rather than adding syntax or format guidance, so baseline 3 applies.

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 ('Builds a verification template') plus what the template contains (JSON Schema, cross-field rules, bounds) and where it comes from (1-10 sample outputs). The phrase 'by fixed rules, no model' distinguishes it from inference-by-model siblings such as ask_sarnai without needing to name them.

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?

Usage is only implied: the sample-count window and 'varied samples show which fields are optional' hint at when the tool applies, but there is no explicit when-to-use/when-not-to-use statement and no named alternative (e.g. get_template for existing templates, prepare_verification for using one). An agent must infer the routing.

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.