search_jmeter_docsSearch the Apache JMeter documentation on docs.jmeter.ai. Returns the most relevant pages with titles, URLs, and snippets. Use for any question about JMeter test plans, components, functions, properties, distributed testing, reports, or troubleshooting.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query, e.g. "how to correlate dynamic values" or "thread group ramp up" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the transparency burden. It clearly states the output format ('recent pages with titles, URLs, and snippets') and implies a read-only operation. It does not mention any side effects or limitations, but for a search tool this is reasonably transparent. The lack of statement about being non-mutating is a minor gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: first defines the action and source, second describes the output and intended use. No filler or irrelevant information. Front-loaded with the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with a single parameter and no output schema, the description adequately covers what it does and returns. It mentions the domain (docs.jmeter.ai) and the types of results. It could be enhanced by noting how results are ordered or if there are limits, but overall it is sufficiently complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides 100% coverage for the single 'query' parameter, including an example. The description adds no additional parameter context beyond what the schema already contains. Per the rubric, baseline 3 is appropriate when schema coverage is high and the description doesn't supplement it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Search') and the resource ('Apache JMeter documentation on docs.jmeter.ai'). It specifies the return type ('pages with titles, URLs, and snippets'), which fully distinguishes it from sibling tools like get_jmeter_page (which likely retrieves a specific page).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly states when to use it: 'Use for any question about JMeter test plans, components, functions, properties, distributed testing, reports, or troubleshooting.' However, it does not mention alternatives or exclusions, such as pointing to get_jmeter_page for retrieving a known page. So it has clear context but no contrast with siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool addresses a clearly distinct need: conversion, validation, workload math, distributed planning, OS tuning, docs search/page retrieval, error lookup, property lookup, and script recipes. Even the doc-related tools are complementary: search returns links, while get_jmeter_page fetches full content.
All tool names follow a consistent lowercase snake_case verb_noun pattern: calculate_, convert_, get_, lint_, lookup_, plan_, search_, tune_. The verbs clearly signal the action and the nouns clearly signal the target, making the set predictable.
Ten tools is well-scoped for a JMeter-specific MCP server. Each tool targets a meaningful area: test plan generation, validation, workload modeling, distributed execution, OS tuning, documentation, and troubleshooting. None feel redundant or superfluous.
The surface covers the main JMeter workflow: converting HTTP input to JMX, linting it, fetching scripting recipes, planning distributed runs, tuning the OS, and researching docs/errors. A minor gap is the lack of a general raw JMX builder or meaningful coverage for non-HTTP protocols, but most practical JMeter use cases are addressed.