Skip to main content
Glama

Statistics for one tweak

tweak_stats

Retrieve measured FPS results for one tweak and hardware class, including average reward, sample size, machine count, 95% confidence interval, and a verdict on whether an effect was measured.

Instructions

What was actually measured for one tweak on one hardware class: average reward, number of measurements, number of distinct machines, a 95% confidence interval and a verdict. The verdict is 'no effect measured' whenever the interval still covers zero.

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": {
      "tweak_id": "<tweak_id>",
      "hardware_class": "<hardware_class>"
    },
    "name": "tweak_stats"
  }
}

Input Schema

NameRequiredDescriptionDefault
tweak_idYesTweak id, as returned by list_tweaks
hardware_classYesHardware class, as returned by list_hardware_classes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations at all, the description carries the full behavioral burden, and it does disclose the verdict rule ('no effect measured' whenever the interval covers zero), which is real semantic context an agent could not derive elsewhere. It stops short of covering edge cases such as what happens when zero measurements exist or how unknown ids are handled.

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 sentences, no filler, and the returned-fields list is front-loaded immediately after the scope statement. Every clause conveys information the agent needs to interpret the response.

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?

Because there is no output schema, the description must characterize the return values, and it does so field by field, including the verdict semantics. The remaining gap is failure/empty-data behavior for a read tool with two required ids, which is a modest omission rather than a blocking one.

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%: both parameters are documented in-schema and even point at the sibling tools that produce the ids. The description adds no additional meaning about parameter format or constraints, so the baseline 3 applies.

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 names a specific resource (statistics for one tweak on one hardware class) and enumerates exactly what the payload contains: average reward, measurement count, distinct machine count, 95% CI, and verdict. This is clearly distinct from the list_* siblings and from recommend/simulate_session, which produce rather than report measurements.

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?

The phrase 'what was actually measured' implicitly signals this is for empirical results as opposed to simulated or recommended outcomes, which is useful context. However, there is no explicit when-to-use/when-not statement and no sibling is named as an alternative, so an agent must infer the routing.

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