Skip to main content
Glama

agentlens_benchmark

Create and manage A/B benchmarks for comparing agent configurations, track metrics like cost and latency, and obtain statistical results.

Instructions

Manage A/B benchmarks: create, list, check status, get results, and control lifecycle.

When to use: To set up controlled experiments comparing different agent configurations (models, prompts, parameters), track which variant performs better, and get statistical results.

Workflow:

  1. create — Define a benchmark with 2+ variants and metrics

  2. Tag sessions with variant tags during data collection

  3. start — Transition benchmark to running

  4. status — Check progress (session counts per variant)

  5. results — Get statistical comparison with p-values

  6. complete — Finalize the benchmark

Actions:

  • create: Set up a new benchmark (name, variants[], metrics[])

  • list: List benchmarks, optionally filter by status

  • status: Get benchmark detail with per-variant session counts

  • results: Get formatted comparison table with statistical analysis

  • start: Transition benchmark to running state

  • complete: Transition benchmark to completed state

Example: agentlens_benchmark({ action: "create", name: "GPT-4o vs Claude", variants: [{name: "gpt4o", tag: "v-gpt4o"}, {name: "claude", tag: "v-claude"}], metrics: ["cost", "latency", "success_rate"] })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform
nameNoBenchmark name (required for create)
descriptionNoBenchmark description
variantsNoVariants to compare (required for create, min 2)
metricsNoMetrics to track (e.g., ["cost", "latency", "success_rate"])
minSessionsNoMinimum sessions per variant before results are meaningful
agentIdNoAgent ID to scope the benchmark to
statusNoFilter by status (for list action)
benchmarkIdNoBenchmark ID (required for status/results/start/complete)
Behavior3/5

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

Annotations are absent, so the description fully carries the burden. It describes lifecycle actions (create, start, complete) and what each does, but it omits details about side effects, data persistence, or required permissions. The behavioral profile is adequate but not deep.

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?

The description is well-structured with headers and sections, and it front-loads the main purpose. It is moderately concise; every sentence adds information, though it could be slightly trimmed without loss.

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?

Given the tool's complexity (9 parameters, 1 required, no output schema), the description covers the main actions, workflow, and key parameters. It lacks details on return values, but the example and action list provide good context. Annotations would have helped, but overall it's fairly complete.

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%, but the description adds value by explaining the workflow, listing required parameters per action (e.g., 'name required for create'), and providing an example. This enriches understanding beyond the raw schema.

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 clearly states the tool's purpose: 'Manage A/B benchmarks: create, list, check status, get results, and control lifecycle.' It uses specific verbs and a concrete resource (benchmarks), and it distinguishes itself from sibling tools by focusing on experiment lifecycle management.

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 includes a 'When to use' section that explains the context ('set up controlled experiments comparing different agent configurations') and provides a workflow. While it doesn't explicitly exclude alternatives, the workflow and action list give clear guidance on typical use cases.

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/agentkitai/agentlens'

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