Skip to main content
Glama
Coval MCP Server

Coval MCP Server

Official
by coval-ai

List runs

list_runs
Read-onlyIdempotent

Retrieve evaluation runs with optional filters and sorting, returning run IDs, statuses, and tags to help monitor agents, personas, and test sets.

Instructions

List evaluation runs. Each run = agent + persona + test_set. Returns run_id, status, tags. Filter by tag: filter='tag="regression"'.

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": "list_runs"
  }
}

Input Schema

NameRequiredDescriptionDefault
filterNoFilter expression (e.g., status="COMPLETED")
order_byNoSort order (e.g., "-create_time" for newest first)
page_sizeNoNumber of results per page (1-100, default 50)
page_tokenNoToken for retrieving the next page of results

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • removedInput schema / additionalProperties
      Removed value: -false
  2. Changed4 schema fields changedv0.4.1
    • addedInput schema / description
      Added value: +"Input for listing evaluation runs"
    • addedInput schema / properties / filter / maxLength
      Added value: +1000
    • addedInput schema / properties / order_by / maxLength
      Added value: +200
    • addedInput schema / properties / page_token / maxLength
      Added value: +2048
  3. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description goes beyond them by disclosing the conceptual composition of a run and the shape of the return (run_id, status, tags), though it says nothing about pagination behavior or ordering defaults.

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?

Four short sentences, front-loaded with the resource, then composition, then return shape, then the one non-obvious syntax detail. Nothing is padded and the most useful example is last where it belongs.

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 usefully names the returned fields, and the filter example covers the most likely failure mode (bad filter syntax). Pagination semantics are left entirely to the schema, which is acceptable given its explicit page_size/page_token descriptions.

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 all four parameters are already documented with examples and bounds. The description only adds a second filter syntax example (tag="regression") beyond the schema's status example, which is a marginal gain — the baseline 3 applies.

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 ("List evaluation runs") and immediately defines what a run is (agent + persona + test_set), which is genuinely clarifying. It does not explicitly distinguish itself from get_run or list_scheduled_runs, but the list-vs-get split is obvious from the names.

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: you call it to enumerate runs, and the tag-filter example hints at a filtering use case. There is no explicit statement of when to prefer get_run for a single run or when tag filtering is preferable to other filters, so the agent must infer.

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