Skip to main content
Glama
respanai

Respan MCP Server

Official
by respanai

create_evaluator

Create a grader to score LLM outputs with customizable criteria: LLM-based, code-based, or human evaluation. Specify type, scoring format, and optional passing conditions.

Instructions

Create a new evaluator (grader). Evaluators score LLM outputs.

REQUIRED: name, type, score_value_type.

TYPES:

  • "llm": LLM-based evaluation. Requires llm_config with model + evaluator_definition.

  • "code": Code-based evaluation. Requires code_config with eval_code_snippet.

  • "human": Manual human evaluation. No automation config needed.

SCORE VALUE TYPES: numerical, boolean, percentage, single_select, multi_select, json, text

FOR LLM EVALUATORS: llm_config must include:

  • model (required): e.g. "gpt-4o-mini"

  • evaluator_definition (required): Jinja2 prompt template. MUST contain {{output}}. Use {{input}} for user question, {{expected_output}} for ground truth.

  • scoring_rubric (recommended): Scoring instructions appended after definition.

  • temperature, max_tokens, top_p, etc. (optional)

EXAMPLE - Boolean LLM grader: { "name": "Hallucination Check", "type": "llm", "score_value_type": "boolean", "llm_config": { "model": "gpt-4o-mini", "evaluator_definition": "Score whether this output hallucinates.\nInput: {{input}}\nOutput: {{output}}\nReturn true or false.", "temperature": 0 } }

EXAMPLE - Numerical LLM grader with rubric: { "name": "Response Quality", "type": "llm", "score_value_type": "numerical", "score_config": { "min_score": 1, "max_score": 5 }, "passing_conditions": { "primary_score": { "operator": "gte", "value": 3 } }, "llm_config": { "model": "gpt-4o", "evaluator_definition": "Evaluate the quality of this response.\nInput: {{input}}\nOutput: {{output}}", "scoring_rubric": "1=terrible, 2=poor, 3=ok, 4=good, 5=excellent" } }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesEvaluator name.
typeYesEvaluator type: llm (requires llm_config), code (requires code_config), or human.
llm_configNoLLM automation config. Required for type="llm". Must include model + evaluator_definition.
code_configNoCode automation config. Required for type="code".
descriptionNoEvaluator description.
score_configNoScore type configuration.
evaluator_slugNoUnique slug identifier. Auto-generated if not provided.
score_value_typeYesScore format: numerical, boolean, percentage, single_select, multi_select, json, text.
passing_conditionsNoConditions for passing. Example: { "primary_score": { "operator": "gte", "value": 3 } }
categorical_choicesNoChoices for single_select/multi_select score types.
Behavior3/5

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

With no annotations provided, the description carries the full burden. It usefully explains config requirements, the mandatory {{output}} placeholder, and provides examples, but it does not disclose side effects, validation behavior, permissions, idempotency, or what the API returns upon creation. This is adequate but not rich behavioral disclosure.

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 long but every section earns its place: required fields, type definitions, SCORE VALUE TYPES, llm_config requirements, and two complete examples. It is front-loaded with the core purpose and uses clear headers and formatting, making it easy to scan for the most important information without unnecessary filler.

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?

For a complex tool with 10 parameters, nested objects, no output schema, and no annotations, the description is highly complete: it covers type-specific requirements, required vs optional fields, and gives end-to-end examples. It falls slightly short of a 5 because it does not describe the response shape, acknowledgment behavior, or common validation errors after creation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents every parameter (100% coverage), so the baseline is 3. The description adds meaningful value beyond that: it explains the required combination of type-specific configs, provides concrete JSON examples, clarifies the mandatory {{output}} template variable, and demonstrates score_config and passing_conditions usage. This justifies a score above baseline.

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 opens with 'Create a new evaluator (grader)' and immediately defines what evaluators do ('score LLM outputs'). This is a specific verb+resource pairing that clearly differentiates the tool from sibling tools like list_evaluators, update_evaluator, and test_evaluator.

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 provides clear usage context by listing REQUIRED fields and explaining the three evaluator types (llm, code, human) with their corresponding config requirements. It does not explicitly enumerate alternatives, but the creation-focused purpose and the type-specific guidance are strong enough for an agent to know when to use this tool.

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/respanai/respan-mcp'

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