Skip to main content
Glama

Search HVAC articles

search_articles
Read-onlyIdempotent

Search AtlantFlow's published HVAC articles. Use when a homeowner asks why their AC does something (not cooling, freezing up, strange noises, high humidity, no heat) or how to troubleshoot or maintain a system in South Florida. Returns ranked articles with title, URL, summary and date; call get_article for the full text. Cite the URL when answering.

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": {
      "query": "<query>"
    },
    "name": "search_articles"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax results (1-10).
queryYesWhat the homeowner asks, in plain words, e.g. 'AC freezing up', 'humidity in house', 'strange noise from outdoor unit', 'no heat'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: results are ranked, each hit bundles title/URL/summary/date, and full text requires a second call. It stops short of disclosing result-set sizing, empty-result behavior, or anything about the index's freshness.

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?

Four short sentences, each doing distinct work: identity, trigger conditions, return shape plus next-step tool, and a citation instruction. The triggering conditions are front-loaded ahead of the mechanical details, so an agent can decide before reading on.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only two parameters, full schema coverage, and no output schema, the description supplies the missing return-value picture (ranked list with title, URL, summary, date) and names the escalation path to get_article. It also adds the operational instruction to cite the URL, which no structured field conveys.

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%, with both query and limit documented including examples and the 1-10 bound, so the schema carries the load. The description reinforces the query intent ('what the homeowner asks, in plain words') with symptom phrasing but adds no syntax, format, or limit behavior beyond the structured fields. 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?

States a specific verb and resource ('Search AtlantFlow's published HVAC articles') with a clear domain scope. It is immediately distinguishable from the sibling get_article, which the description explicitly names as the follow-up for full text, and from list_articles by virtue of being query-driven.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use triggers ('why their AC does something') with an enumerated list of symptoms, plus the maintenance/troubleshooting case. It also handles the when-not case: for full text, route to get_article instead. Nothing is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources