Skip to main content
Glama
Sign In

AskMyEV

by com.askmyev
OverviewDiscussionsAdmin

Diagnose alerts

diagnose_alerts
Read-only

Active and recent Tesla alerts for the car (last 30 days by default), plus low-tire flags from the latest saved snapshot, each with a link to Tesla's public Service Manual for that model and a search link for the alert name. Use it when the user asks what a warning means or how to diagnose/fix it, then walk them through the manual's steps. Answers from saved data only; never contacts or changes the car. Tesla alerts are not full diagnostic trouble codes. High-voltage components are for trained professionals only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "diagnose_alerts"
  }
}

Input Schema

NameRequiredDescriptionDefault
vinNoVehicle VIN (full, or its last 4-6 characters). Required when the account has more than one car (call list_vehicles first and ask the user which car). Optional with one car. Every car on the owner's Tesla account is covered by the plan.
daysNoHow many days back to look (default 30, max 365).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover read-only, non-destructive, and closed-world, and the description reinforces rather than contradicts them with "Answers from saved data only; never contacts or changes the car." It adds genuinely useful context beyond the annotations: the data source is a saved snapshot, outputs include documentation links, and alerts are explicitly not full diagnostic trouble codes. It stops short of describing pagination or volume of results, but the self-imposed safety framing (high-voltage warning) is a meaningful disclosure.

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?

Front-loaded with what is returned, then when to use it, then the behavioral and safety constraints — a sensible ordering with no wasted opening. It runs slightly long, with the two closing caution sentences reading as boilerplate, though each is defensible for a safety-adjacent automotive tool.

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?

No output schema exists, yet the description compensates by naming the return contents (alert records, low-tire flags, manual link, search link). For a two-parameter read-only tool this is close to complete; the only real gap is the unstated relationship to get_alert_history, which leaves a routing ambiguity.

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 coverage is 100%, so both parameters are already documented, including the 30-day default, the 365-day cap, and the VIN multi-car rule. The description restates the 30-day default but adds no new semantics such as VIN formatting edge cases or timezone behavior for the day window. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

States a specific verb and resource: active and recent alerts for the car, plus low-tire flags from the latest snapshot, each enriched with Service Manual and search links. This is far more concrete than the title. However, it never distinguishes itself from the sibling get_alert_history, so an agent cannot tell from the description alone which of the two to call for alert data.

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

Usage Guidelines4/5

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

Gives an explicit trigger condition: "Use it when the user asks what a warning means or how to diagnose/fix it," and even prescribes the follow-on behavior of walking the user through the manual steps. There are no explicit exclusions or named alternatives (e.g., get_alert_history for a raw historical list), which keeps it below a 5.

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

All AskMyEV 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