Skip to main content
Glama

Get one building permit

get_permit
Read-onlyIdempotent

One building permit by permitId. representation="standard" (the default) has every party named on the permit with the phones and emails it printed, the inspections summary, value, size, and building type. "compact" is the short card. "full" adds the history, every inspection, fees, property owners, and plannedProjectId when the permit is linked to a planned project. includeSourceText=true also returns the text the permit was read from (it implies full; long text is cut and the response says so). Counts as one export record on County, State, and National, or 1 credit on API Only and the trial, the first time this account receives this permit's current content. The source text counts with the permit record: 1 export record (or credit) per new or changed permit across both, and nothing more if the account already has it. A permit with no source text on file returns without it, with a note, and nothing extra is charged. Re-reading an unchanged permit does not use credits. detailLevel "summary" means Boardwalk has only the city's list entry for this permit, so the contractor or value may be on the city's own page (sourceUrl). A private individual's phone or email can be withheld (contactWithheld). withheld "upgrade" means homeowner phones and emails need a paid plan, and the user's plan does not include them; "acknowledge" means the user has to accept the homeowner contact rules once in the Boardwalk web app, and then they show. hasPhone and hasEmail say which exists. When anything on a permit is withheld, every phone and email in its source text and its written text (descriptions, summaries, titles, notes, inspections, history; counted in textContactWithheld) shows as "[phone withheld]" or "[email withheld]", business lines included; quote business phones and emails from the permit's parties instead. Name every party the result returns; mention withholding only for a party that carries contactWithheld. The contact exists: never call it missing or not on the permit, and never guess a number. get_credit_balance returns the remaining balance.

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": {
      "permitId": "<permitId>"
    },
    "name": "get_permit"
  }
}

Input Schema

NameRequiredDescriptionDefault
permitIdYesA permit id (permitId on a permit record).
representationNostandard (default): every party with printed phones and emails. full adds history, inspections, fees, owners. compact is the short card.
includeSourceTextNoAlso return the permit's source text. Implies full. One permit at a time; never in a loop.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past the readOnly/idempotent annotations by disclosing the credit model (one export record the first time the account receives the permit's current content, free on unchanged re-reads), source-text truncation with an in-response note, and the detailLevel "summary" limitation. It also explains the withholding mechanics (upgrade vs. acknowledge, textContactWithheld placeholders) in enough depth to prevent misinterpretation of the payload.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and representation modes are front-loaded, but the text is a dense run-on covering billing, detailLevel, withholding, and response-writing instructions in one unbroken block. Almost every sentence carries information, yet the withholding section and the directives about how to phrase parties/contacts add bulk that could be tightened or structured.

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?

With no output schema and a complex paid, sometimes-redacted payload, the description covers what each representation returns, how source text behaves, how credits are consumed, and what the withheld states mean. An agent has what it needs to call the tool and interpret the result without further documentation.

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 the enum values and the includeSourceText flag are already documented structurally. The description adds real meaning on top — includeSourceText's cost impact, its implication of full, and truncation — but most of the representation detail restates the schema. A 3 reflects the baseline plus modest added value.

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?

Opens with a concrete verb-and-resource statement: "One building permit by permitId," and the scope word "one" implicitly separates it from the list/sync siblings. It never names an alternative tool, so the differentiation is inferred rather than stated.

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 selection guidance for its own parameters: standard is the default, compact is "the short card," full "adds the history, every inspection, fees, property owners," and includeSourceText implies full. It lacks guidance on how to obtain a permitId or when to prefer this over get_permits_sync, so no explicit alternatives or exclusions are named.

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