API Tool Calls

Driveway Cost Calculator

driveway_cost

Read-onlyIdempotent

Estimate driveway replacement costs for a given size. Returns national installed ranges with no published typical figure. One call compares all ten surfaces. Base, drainage and permits are not priced; removal is priced only for an existing concrete driveway. Includes unpriced checks, two separate national reference cards and dated sources. Pure arithmetic, no network or model.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "surface": "concrete_standard",
      "sections": [
        {
          "width_ft": 24,
          "length_ft": 12
        }
      ]
    },
    "name": "driveway_cost"
  }
}

Input Schema

Name	Required	Description	Default
`surface`	Yes	Chosen installed surface; one call compares all ten surfaces.
`existing`	No	Existing driveway surface. Removal is priced only for existing concrete.	none
`sections`	Yes	1–10 sections, each 1–10,000 sq ft; total 20–10,000 sq ft. Use length_ft + width_ft OR area_sqft per section.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 4, 2026
RemovedOct 4, 2026
AddedOct 3, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive and closed-world behavior, so the bar is lower; the description still adds that it is 'pure arithmetic, no network or model' and discloses what is not priced and what dated sources back the ranges.

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?

Four compact sentences, front-loaded with the core estimate purpose and then the scoping caveats. Dense but each clause carries information, though 'Includes unpriced checks' is vague relative to its neighbours.

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, and the description compensates by describing the return as national installed ranges with no typical figure plus two reference cards and dated sources. Slightly imprecise about result structure, but sufficient to call the tool correctly.

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 surface, existing and sections are already fully documented, and the description largely restates them ('for a given size', removal only for existing concrete). Baseline 3 is appropriate where the schema does the heavy lifting.

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 ('Estimate driveway replacement costs') scoped by size, and distinguishes itself from surface-adjacent siblings (concrete_calculator, flooring_cost, fence_cost) by naming the ten surfaces it compares in one call.

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 clear context: one call compares all ten surfaces, and it explicitly scopes out base, drainage and permits, and limits removal pricing to existing concrete. It stops short of naming a sibling alternative to use instead, but the exclusions make the right call obvious.

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

All API Tool Calls tools Inspect

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

Need Help?