Skip to main content
Glama

fuel_price

Read-only

Finds the lowest-priced nearby diesel or petrol station within about 5 km and returns its price, distance, and price age in one sentence.

Instructions

Find the cheapest fuel near a point; changes nothing. Names the cheapest station within about 5 km, its price, how far it is and how old the price is, in one sentence. Read 'say' aloud.

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": "fuel_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoThe phone's latitude, if known.
lonNoThe phone's longitude, if known.
fuelNoThe fuel: diesel, petrol95 or petrol98. Diesel when the user names none.diesel
accuracy_mNoHow exact the position is, in metres; 100 if not given.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

The readOnlyHint annotation already establishes that nothing is mutated, and the description reinforces and extends it with 'changes nothing', the ~5 km search radius, and the freshness caveat implied by returning 'how old the price is'. That is meaningful behavioral context beyond the annotation, though it says nothing about failure modes when no station is found or about how the radius interacts with positional accuracy.

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 short sentences front-load the purpose and scope with no wasted wording, and the return contract is stated compactly. The trailing instruction 'Read "say" aloud' is terse and somewhat cryptic out of context, costing a bit of clarity.

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?

An output schema exists, so the description need not document return structure, and it still sketches the one-sentence answer. For a four-parameter read-only lookup, the main remaining gap is behavior when coordinates are absent or no station exists within 5 km.

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%, so all four parameters, including the diesel default and the enum values, are already documented in structured form. The description adds no syntax or interpretation beyond 'near a point', which merely restates lat/lon, so the correct baseline of 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 states a specific verb and resource ('Find the cheapest fuel near a point') and adds the operational scope ('within about 5 km'), plus what the answer contains (station, price, distance, price age). That is precise enough for an agent to know exactly what this call produces, even without sibling tools to distinguish from.

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 'near a point' and 'cheapest', but there is no explicit statement of when a user request should route here, no mention of what to do when the location is unknown (lat/lon are nullable), and no exclusions. The sibling list is empty, so the omission of alternatives is acceptable, but the trigger conditions remain implicit.

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

Deploy Server

Other Tools