Skip to main content
Glama

Create a building permit alert

create_permit_alert

Creates a recurring building permit alert. Requires name and filters, using the search_permits filter names (for example cities, workTypes, valueMin). cadence.frequency is daily, weekly, or monthly. Optional share block {mode, userIds, optOutUserIds}; sharing requires a paid plan. New matches arrive in the email digest. The same limits as planned-project alerts: filters must name a place (states, counties, or cities), with at most 5 states and 25 counties or cities, unless the plan is nationwide; and an account holds at most 25 active permit alerts (planned-project alerts are counted separately). permitIds, contractorKeys, placeKey, and bbox cannot be saved on an alert. A refusal names the rule (alert_geography_required, alert_geography_too_broad, or alert_limit_reached); relay it and offer to narrow the place or pause an alert. The alert follows the plan area. Writing the alert does not use credits. An alert created here is API-made, so its scheduled runs are charged: each new or changed permit a run adds counts as one export record, or 1 credit on API Only and the trial. Say so, with preview_permit_alert's count, before creating. This call does not send the digest. Confirm with the user first: the name, the place, the work types, and the value floor.

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": {
      "name": "<name>",
      "filters": "<filters>"
    },
    "name": "create_permit_alert"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe alert's name, e.g. "Pool permits over $50k – Lehi".
shareNoTeam sharing. Any member of a shared alert may read, edit, run and delete it. Sharing requires a paid plan.
activeNofalse pauses the alert.
cadenceNoHow often new matches are emailed: daily, weekly, or monthly.
filtersYesAt least one filter, in the search_permits names, e.g. {"cities":["Lehi"],"workTypes":["pool"],"valueMin":50000}.
findContactInfoNotrue runs Find Contact Info on each run's new permits, up to 200 a run: 1 credit per permit only when it adds an email, phone, or personal LinkedIn profile the permit did not print. Homeowners are never looked up. Confirm with the user before turning it on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only say this is a non-read-only, non-idempotent, non-destructive write; the description adds far more — sharing needs a paid plan, an API-made alert's runs are billed as export records or 1 credit on API Only/trial, the write itself does not consume credits, and the call does not send the digest. The refusal-code contract (alert_geography_required, alert_geography_too_broad, alert_limit_reached) and the list of fields that cannot be saved are unusually concrete behavioral 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?

Purpose and the required confirm-then-preview flow are front-loaded, and nearly every sentence carries operational weight (limits, billing, refusal codes, what not to save). It is dense but slightly overpacked, and a few clauses simply repeat schema content, notably "cadence.frequency is daily, weekly, or monthly," which the enum already states.

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?

For a 6-parameter tool with nested objects and no output schema, the description covers the missing pieces an agent would otherwise guess at: billing consequences of the resulting runs, sharing prerequisites, the cap on activations, unsupported filter keys, and the required user-confirmation step. Nothing material needed to invoke it correctly appears absent.

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%, so the baseline would be 3, but the description adds real meaning: filters use search_permits names with a concrete example, share is described as a "share block {mode, userIds, optOutUserIds}" with the paid-plan gate, and the geography/count caps constrain what filter values are legal. Minor overlap remains where it restates the cadence enum already in the schema.

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?

Opens with a specific verb and resource ("Creates a recurring building permit alert"), and distinguishes itself from the planned-project alert tooling by repeatedly naming that separate limit pool and by pointing at preview_permit_alert before creation. An agent can tell this apart from create_alert, update_permit_alert, and preview_permit_alert from the description alone.

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?

Explicitly routes the agent through preview_permit_alert's count before creating, and states a confirmation protocol: "Confirm with the user first: the name, the place, the work types, and the value floor." It also gives hard when-not conditions (place required, max 5 states / 25 counties or cities, 25-alert cap) and tells the agent how to react to each refusal code.

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