Skip to main content
Glama
Sign In

HouseExhale

by io.github.attachmentnerd
OverviewDiscussionsAdmin

Explain a CO₂ reading

explain_co2_reading
Read-only

Explains a bedroom CO₂ reading against the precautionary 800 ppm average-while-asleep goal: band, distance from the goal, whether the measurement is comparable, signs of a monitor reading low, and free fixes with trade-offs. The goal is not a health limit. Door-open nights appear only as one-night tests, not fixes.

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": {
      "ppm": "<ppm>",
      "measured": "<measured>"
    },
    "name": "explain_co2_reading"
  }
}

Input Schema

NameRequiredDescriptionDefault
ppmYesThe reading in parts per million
roomNoWhere it was measured (default bedroom)
measuredYesnight_average: the recorded average while asleep. overnight_high: the highest recorded number overnight. spot: one reading at one moment. A morning spot reading is not a recorded overnight high or average.
sleepersNoPeople who slept in the room that night, if known

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / measured / description
      Previous value: -"night_average: the average while asleep (a monitor’s recorded night). overnight_high: the highest number overnight (what most monitors show and people remember). spot: one reading at one moment. If unsure, use overnight_high for a morning number and spot for a daytime one."New value: +"night_average: the recorded average while asleep. overnight_high: the highest recorded number overnight. spot: one reading at one moment. A morning spot reading is not a recorded overnight high or average."
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, non-destructive, closed-world, so the safety bar is met structurally. The description adds genuinely non-derivable context: the 800 ppm goal is precautionary and explicitly not a health limit, and door-open nights are treated only as one-night tests rather than fixes. That framing prevents an agent from overstating the result as a medical verdict, which no annotation conveys. It stops short of describing the response shape, but that gap is modest.

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?

Two sentences, front-loaded with the verb and the goal, with the caveats pushed to the end where they belong. The middle clause is a dense list but every item names a distinct output facet. Slightly list-like and could be tightened, but nothing is redundant.

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?

With no output schema, the description carries the burden of telling the agent what comes back, and it does so by naming each returned facet including the fixes and their trade-offs. The one loose end is that it frames the tool as bedroom-only while the schema offers room='other'; an agent gets no signal about how a non-bedroom reading is handled.

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% and the enum descriptions for 'measured' already spell out night_average vs overnight_high vs spot, including the caveat about morning spot readings. The description adds only a light connection between 'measured' and the average-while-asleep goal ('whether the measurement is comparable'). The schema does the heavy lifting, so 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 pairs a specific verb with a specific resource and scope: it explains a bedroom CO₂ reading against the 800 ppm average-while-asleep goal. It then enumerates the exact facets produced (band, distance from goal, comparability, signs of an under-reading monitor, fixes with trade-offs), which distinguishes it from all four siblings, none of which analyze a reading.

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 rather than stated: the agent can infer this is the tool for interpreting a CO₂ number, and the ppm/sleepers inputs reinforce that. But there is no explicit when-to-use or when-not-to-use guidance, and no routing such as 'use check_ventilation_unit for hardware faults instead' despite an obvious adjacency.

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

All HouseExhale toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources