Skip to main content
Glama

propose_eval_criteria

Generates proposed evaluation criteria from a use case hint and optional sample calls, using an LLM judge to draft rubrics for measuring prompt quality.

Instructions

Have an LLM judge (gpt-4o-mini) propose eval criterion candidates from a one-line useCaseHint (e.g. "customer support bot") and optional sampleCallIds (representative calls from your account, up to 5) (POST /v1/eval-criteria/propose). An AI agent can finish "propose criteria to measure our prompt quality" in one prompt. Pro+ only (the backend enforces the plan gate + budget gate); nothing is INSERTed (propose only — adoption is a separate step via create_eval_criterion, structurally limiting LLM-hallucination impact). Decrypt failures for sampleCallIds are reported in partialFailures (the LLM call still runs without samples). Privacy note for prompt samples: with sampleCallIds, the backend decrypts those calls' prompt/response and sends excerpts (1500 chars each) to OpenAI gpt-4o-mini. This re-sends data your SDK originally sent to OpenAI/Anthropic, so no new vendor is added, but be aware it may reach an OpenAI model different from your own LLM calls. If that is a concern, run with useCaseHint only. Results are advisory: the returned criteria are LLM proposals and may include semantically weak rubrics (overuse of "helpful", duplicates) even when structurally valid. User review before adoption is recommended; do not feed them blindly into create_eval_criterion. Returns { criteria: [{ name (snake_case 32 chars), rubric (1-200), scaleMin (=1), scaleMax (5 or 10), reasoning (1-200) }], partialFailures: string[], budgetSpentUsd, proposedRawCount (raw count returned by the LLM), droppedCount (entries removed by the validator) }. Audit: emits an eval.propose_criteria event to the audit log.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
maxCriteriaNoMax number of criteria to return (1-10, default 5)
useCaseHintYes1-2 line description of the intended use case (e.g. "customer support bot for e-commerce returns + refunds"; 1-500 chars, required)
sampleCallIdsNoArray of call_ids from your account passed as context (optional, up to 5, [A-Za-z0-9_-]{1,128}). Grounds the LLM's proposals in your own data
Behavior5/5

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

No annotations provided, but description fully covers behavior: nothing is inserted, decrypts samples, sends excerpts to OpenAI, results are advisory, includes return structure and audit event.

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?

Description is detailed but front-loaded with key information. Each sentence adds value; however, it could be slightly more concise without losing clarity.

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

Completeness5/5

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

Given no output schema, the description thoroughly explains return structure, including partialFailures and budgetSpentUsd. Covers edge cases like decrypt failures. Complete for a 3-param tool.

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?

Schema coverage is 100%, so baseline is 3. Description adds value by explaining the purpose of each parameter and behavioral aspects (e.g., sampleCallIds grounds proposals).

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?

Description clearly states the tool proposes eval criterion candidates using an LLM judge from a useCaseHint and optional sampleCallIds. It distinguishes from sibling create_eval_criterion by noting adoption is a separate step.

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

Usage Guidelines5/5

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

Explicitly states when to use ('propose criteria to measure our prompt quality'), mentions prerequisites (Pro+ only), provides alternative for privacy (useCaseHint only), and recommends user review before adoption.

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/argosvix/mcp-server'

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