Skip to main content
Glama
nyc-311-mcp

nyc-311-mcp

ll47_directory_assistance_report

Rebuilds a monthly directory-assistance report from NYC 311 call-center inquiry data, listing calls by topic for a month and fiscal year to date, with data limits noted.

Instructions

Rebuilds the monthly directory-assistance report of former Charter § 1075(c) (Local Law 47 of 2005; repealed by Local Law 69 of 2023), as far as the open data allows: calls to 311 agents for a month and the fiscal year to date, by topic, from NYC Open Data's 311 Call Center Inquiry dataset (wewp-mm3p). Marked limited: the dataset cannot tell directory-assistance calls from others, and its agency and call-resolution columns are blank in recent years, so there is no breakdown by agency. Queries NYC Open Data (one query per month, cached; the month in progress is asked again after an hour). A month call fetches only that month; its fiscal year to date uses saved months. A fiscal_year call answers within about 12 s: saved months at once, others listed as still loading while they keep loading (an incomplete period shows each saved month's count and a partial sum, labeled, never a total); asking again a minute later finishes it. A BetaNYC rebuild from NYC Open Data, not the City's official report. No ZIP codes, nothing before 2020.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ll47_directory_assistance_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many topics to list (default 50).
monthNoMonth, YYYY-MM; the answer also covers the fiscal year to date through it. Default: the newest complete month. Not with fiscal_year.
fiscal_yearNoNYC fiscal year: 2027 or 'FY2027' = 2026-07-01 to 2027-06-30, cut to the data if not over. Not with month.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A4.1/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full behavioral burden, and it does so thoroughly: it discloses caching, one query per month, re-querying the in-progress month after an hour, roughly 12 s latency for fiscal_year calls, labeled partial sums that are never presented as a total, and dataset gaps (cannot isolate directory-assistance calls; agency and call-resolution columns blank in recent years). It also identifies the source and clarifies that this is a BetaNYC rebuild, not the City's official report.

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?

The description is front-loaded with purpose and limitations, and nearly every sentence contributes distinct operational information about data limits, caching, latency, or partial results. It is dense and would be easier to scan with bullets, but there is little wasted repetition.

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 complex report tool with zero required parameters and no output schema, the description covers data source, data limitations, caching behavior, latency, partial-result handling, and scope exclusions. This is enough for an agent to call the tool correctly and understand the main caveats without additional documentation.

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 description coverage is 100%, so the baseline is 3, but the description adds useful meaning beyond the schema by explaining that a month request returns only that month while its fiscal year-to-date relies on saved months, and that fiscal_year returns saved months immediately with others still loading. The limit parameter is left to the schema, but the temporal parameters are clarified in operational terms.

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 specific verb ('Rebuilds') and a named artifact ('monthly directory-assistance report'), then specifies the data source, metric, and period coverage (311 agent calls by topic, month and fiscal year to date). It is highly specific, but it does not mention the sibling ll47_service_request_report or explain why an agent would choose one over the other.

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?

The description implies intended use through its scope constraints ('No ZIP codes, nothing before 2020') and limitations, which help an agent avoid inappropriate requests. However, it gives no explicit when-to-use, when-not-to-use, or alternative-tool guidance relative to siblings such as ll47_service_request_report or draft_311_report.

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