Skip to main content
Glama

Search building permits

search_permits
Read-only

Newly issued building permits with address, permit type, description, contractor, job value and issue date, filtered by area, category, city, zip, distance from a point or zip, multi-trade projects, dates and minimum value, newest first or sorted by job value or urgency. Up to 100 per call. Costs $0.10 in USDC (x402; Base, Solana, Polygon or Arbitrum); no charge when nothing matches.

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": {
      "jurisdiction": "<jurisdiction>"
    },
    "name": "search_permits"
  }
}

Input Schema

NameRequiredDescriptionDefault
zipNo
cityNoCity name, case-insensitive
nearNoOnly permits near a zip code in the area or a "lat,lng" point
sortNonewest first (default), highest job value first, or urgent permits firstnewest
limitNo
sinceNoIssued on or after (YYYY-MM-DD)
untilNoIssued on or before (YYYY-MM-DD)
categoryNoPermit category, e.g. roof, pool, solar, hvac, new_residential
minValueNoMinimum job valuation in USD
multiTradeNoOnly permits at addresses with another type of permit within 90 days (usually bigger projects)
radiusMilesNoRadius around near, in miles
jurisdictionYesArea id, e.g. new-york-ny, miami-dade-fl. Use list_coverage for names.
includeRenewalsNoInclude New York renewals of existing permits (left out by default)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / multiTrade
      Added value: +{
      +  "description": "Only permits at addresses with another type of permit within 90 days (usually bigger projects)",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / near
      Added value: +{
      +  "description": "Only permits near a zip code in the area or a \"lat,lng\" point",
      +  "pattern": "^(\\d{5}|-?\\d{1,3}(\\.\\d+)?,\\s*-?\\d{1,3}(\\.\\d+)?)$",
      +  "type": "string"
      +}
    • addedInput schema / properties / radiusMiles
      Added value: +{
      +  "default": 5,
      +  "description": "Radius around near, in miles",
      +  "maximum": 50,
      +  "minimum": 0.1,
      +  "type": "number"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / sort
      Added value: +{
      +  "default": "newest",
      +  "description": "newest first (default), highest job value first, or urgent permits first",
      +  "enum": [
      +    "newest",
      +    "value",
      +    "urgent"
      +  ],
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / includeRenewals
      Added value: +{
      +  "description": "Include New York renewals of existing permits (left out by default)",
      +  "type": "boolean"
      +}
  4. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description adds substantial operational context: a $0.10 USDC x402 charge across Base, Solana, Polygon or Arbitrum, no charge on empty results, a hard 100-record ceiling, and default ordering of newest first. These are exactly the facts an agent needs before spending money, though the absence of pagination options beyond the 100 cap is not addressed.

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?

Content is front-loaded with the resource and returns, then filters, then the cap and price. The first sentence is long and comma-heavy but every clause carries information; the price sentence clearly earns its place by disclosing cost.

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 no output schema, the description compensates by enumerating returned fields, and it discloses cost, result cap, and sort defaults for a 13-parameter tool. Remaining gaps are minor: no statement on whether more than 100 results can be paged, and 'area' is used loosely relative to the required jurisdiction parameter.

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 already 85%, so the schema carries most parameter meaning (radiusMiles, since/until formats, multiTrade's 90-day rule, includeRenewals default). The description restates the filter set at a high level and confirms sort behaviors, but adds little syntax or edge-case detail beyond what the schema already documents, making baseline 3 appropriate.

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?

The description names a specific resource (newly issued building permits) and enumerates the returned fields (address, permit type, description, contractor, job value, issue date) plus the filter surface, so an agent knows exactly what it retrieves. It does not explicitly contrast itself with siblings such as count_permits or sample_permits, so differentiation is left slightly implicit.

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 context is implied rather than stated: filter-heavy retrieval of permit records, capped at 100 per call, with a cost attached. There is no explicit when-to-use/when-not guidance or routing to alternatives like count_permits for aggregates or permit_stats for summaries, so an agent must infer the boundary.

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