Skip to main content
Glama

Workeey Quote Links

Job Check: permit, license, sales tax

job_check
Read-onlyIdempotent

For a trade job (plumbing, electrical, HVAC, handyman and more) and a place in the United States: whether it needs a permit, which license, whether sales tax goes on the invoice, the official forms, and where to take the waste — each with the official pages quoted, their dates and the day it was checked, and who to confirm with. New York City is researched in full and may ask follow-up questions (a first call with no answers returns them); every state has its license and sales tax answers, and its permit is not researched yet. From Workeey's researched data, read-only, no AI. Not legal or tax advice.

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": {
      "job": "<job>",
      "place": "<place>"
    },
    "name": "job_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYesThe job. replace-faucet-or-sink: Replace a faucet or sink; replace-toilet: Replace a toilet; replace-water-heater-gas: Replace a gas water heater; replace-water-heater-electric: Replace an electric water heater; replace-gas-range-or-appliance: Replace a gas range or connect a gas appliance (stove, oven, dryer); replace-light-fixture: Replace a light fixture; add-or-replace-outlet-or-switch: Add or replace an outlet or switch; install-ceiling-fan: Install a ceiling fan; replace-electrical-panel: Replace an electrical panel; interior-painting: Interior painting; drywall-repair-or-patch: Drywall repair or patch; replace-flooring: Replace flooring; tile-bathroom-or-backsplash: Tile a bathroom or kitchen backsplash; replace-kitchen-cabinets-and-countertops: Replace kitchen cabinets and countertops; install-window-or-through-wall-ac: Install a window or through-wall AC unit; install-ductless-mini-split: Install a ductless mini-split; replace-windows: Replace windows; small-bathroom-remodel-fixtures-in-place: Small bathroom remodel (fixtures stay in place); replace-boiler: Replace a boiler.
workNoFor sales tax, the kind of work: repairTPP: Repairing a thing; repairRealProperty: Repairing a home or building; installation: Installing; newConstruction: New build. Leave it out to see all four answers.
placeYesnyc for New York City, or a state's two-letter code in lower case (ny is New York outside New York City, dc is Washington, DC).
answersNoNew York City only: the job's follow-up questions, each question id → one of its options, in its words or by its number from 1. The answer lists the questions and their options.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that — the NYC follow-up-question round trip where a first call with no answers returns questions, plus the provenance (researched data, quoted official pages with dates, no AI) and the coverage gap for state permits — which is valuable, though return shape and error handling are still only sketched.

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?

Purpose is front-loaded in the first clause and the caveat ('no AI', 'not legal or tax advice') is properly last. The middle coverage sentence is dense and slightly tangled (three clauses about NYC, states, and unresearched state permits), but no sentence is genuinely 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 four parameters, one nested object, no output schema, and non-obvious two-turn behavior in NYC, the definition does the heavy lifting: it describes what comes back, the provenance, the follow-up loop, and the coverage limits. Only edge behavior — what happens with partially filled `answers`, or how permit/license results differ in shape — is left unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with documented enums, so the baseline is 3. The description still earns credit by explaining the purpose of the nested `answers` object through the follow-up-question flow documented in the text, which connects the otherwise cryptic question-id-to-option mapping to a real interaction.

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 names a concrete deliverable set — permit requirement, license, sales-tax treatment, official forms, waste disposal — for a specific input domain (trade job + US place), quoted with sources and dates. That is far more than a restatement of the name 'job_check' and is clearly distinguishable from the quote-oriented siblings (price_check, create_quote_link).

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?

The description tells the agent what coverage to expect per place: NYC is fully researched and may return follow-up questions, states have license and sales-tax answers but no permits yet. That is real when-to-use conditioning on the `place` value, though it never explicitly names when to reach for a sibling or when to stop calling.

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