Skip to main content
Glama

Load test

load_test
Destructive

Send one saved request many times at once and report throughput, latency percentiles, status codes and error samples. Limited to 20 at once, 30 seconds and 5000 requests, to hosts this session may call. Only test systems the developer owns.

Instructions

Send one saved request many times at once and report throughput, latency percentiles, status codes and error samples. Limited to 20 at once, 30 seconds and 5000 requests, to hosts this session may call. Only test systems the developer owns.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "request": "<request>"
    },
    "name": "load_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
rpsNoCap the total requests per second.
requestYesThe request's id, or its name. A name that is used twice needs its folder path in front, as list_requests shows it, such as auth/Login.
requestsNoStop after this many requests.
concurrencyNoRequests in flight at once. Defaults to 5.
duration_secondsNoHow long to keep sending. Defaults to 10 unless requests is given.

Output Schema

NameRequiredDescriptionDefault
hintNo
totalNo
checksNo
configNo
failedNo
latencyNo
stoppedNo
withheldNo
succeededNo
durationMsNo
statusCodesNo
distributionNo
errorSamplesNo
bytesReceivedNo
networkErrorsNo
statusFailuresNo
requestsPerSecondNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.11.4
    • addedOutput schema / properties / checks
      Added value: +{
      +  "type": [
      +    "array",
      +    "null"
      +  ]
      +}
  2. First observedv1.7.19

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true; the description adds real context on top: hard caps (20 concurrent, 30 seconds, 5000 requests), the host-scope restriction ("hosts this session may call"), and the safety caveat about ownership. It stops short of saying whether any persisted state or reports are produced by the run.

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?

Two tight sentences, front-loaded with what the tool does and what it returns, then the limits and the safety constraint. No filler or repetition.

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 destructive, rate-limited load generator with a full output schema, the essentials are present: caps, scope restriction, ownership warning, and reported metrics. Remaining detail (how the request identifier resolves) lives in the schema, which is acceptable given 100% coverage.

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 coverage is 100%, so every parameter is already documented in the schema, including defaults for concurrency and duration_seconds. The description merely restates the same numeric limits (20, 30s, 5000) and adds no new meaning, so the baseline of 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?

Clear verb+resource: 'Send one saved request many times at once

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 implied (you load-test when you want throughput/latency data), and there is one real exclusion: "Only test systems the developer owns." However, it never says when to pick this over send_request for a single call or run_folder for a sequence, so the agent must infer routing.

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