Skip to main content
Glama

Recommend tweaks for a hardware class

recommend

Returns ranked tweak suggestions for a hardware class, ordered by lower confidence bound so proven gains beat noisy results and zero-covering intervals are excluded.

Instructions

Tweaks worth trying on a given hardware class, best first. Ranked by the LOWER bound of the confidence interval, not by the average: that prefers a smaller gain that was measured properly over a larger one seen on two machines. Tweaks whose interval covers zero are excluded.

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": {
      "hardware_class": "<hardware_class>"
    },
    "name": "recommend"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
min_machinesNoIgnore tweaks confirmed by fewer machines than this
hardware_classYesHardware class, as returned by list_hardware_classes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it discloses the two most consequential behaviors: ranking by the lower bound of the confidence interval rather than the mean, and dropping tweaks whose interval covers zero. These are non-obvious selection policies that an agent could not infer from the schema. It stops short of covering performance characteristics, whether results are cached, or the shape of the returned records.

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?

Three compact sentences, front-loaded with the purpose before the ranking rationale. Every clause carries information, though the justification contrast (“a smaller gain measured properly over a larger one seen on two machines”) is more illustrative than strictly necessary.

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 three-parameter, read-style tool with no output schema, the description supplies the ranking rationale and the exclusion rule that determine what an agent actually receives. It omits any indication of the response shape or the effect of the limit parameter, which is a modest gap 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 67%, with hardware_class and min_machines already documented in the schema, so the baseline is 3. The description adds no parameter-level detail at all: limit is never mentioned, and the statistical filtering it explains is not tied to min_machines or any specific input.

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?

The description names a specific resource (“Tweaks worth trying on a given hardware class”) and adds ordering semantics (“best first”), so an agent knows this is a ranked recommendation rather than an enumeration. It does not explicitly distinguish itself from the sibling list_tweaks, leaving the differentiation to inference.

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 by the framing “tweaks worth trying” and by the exclusion rule, which signals this is a curated shortlist rather than the full tweak catalog. However, no alternative is named and there is no explicit “use this instead of list_tweaks when…” statement, so the when-to-use boundary is left implicit.

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