Skip to main content
Glama
nyc-311-mcp

nyc-311-mcp

agency_response

Summarize NYC 311 agency response metrics by district and period, showing request counts, closed and not-yet-closed totals, and median/average days to close.

Instructions

For each agency in a district and period: requests, how many are closed and not yet closed, and the median and average days to close (closed requests only). Optional problem and description filters. From BoardStat (BetaNYC, NYC Open Data, 2020 on); not an official City report. 311 counts are reports, not problems; 'closed' is not 'fixed'.

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": "agency_response"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoRows to list (default 25).
to_dateNoEnd, YYYY-MM-DD, inclusive.
problemsNoBoardStat problem names, e.g. ['HEAT/HOT WATER']; any case.
from_dateNoStart, YYYY-MM-DD, inclusive.
last_daysNoThe last N days of data, ending on the newest request's day (not today).
fiscal_yearNoNYC fiscal year: 2027 or 'FY2027' = 2026-07-01 to 2027-06-30.
descriptionsNo311 descriptors, e.g. ['Blocked Bike Lane']; a missing one is '(none)'.
council_districtNoCouncil district, 1 to 51. Not with community_district.
community_districtNo306, BK06 or 'Brooklyn 6' (all forms: server instructions). Not with council_district.
exclude_descriptionsNoLeave out these descriptions instead of keeping only them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A3.7/5.0
Behavior4/5

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 disclose meaningful caveats: data source and vintage ('From BoardStat (BetaNYC, NYC Open Data, 2020 on)'), non-official status, and the crucial semantic warnings that '311 counts are reports, not problems' and "'closed' is not 'fixed'". It omits any mention of pagination or how many rows an agency breakdown returns.

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 output fields are front-loaded in the first clause, and the caveats are compressed into short semicolon-separated statements with no filler. The density is justified, though the run-on clause structure makes the opening slightly harder to parse than necessary.

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?

For a 10-parameter read with no output schema, the description adequately covers the return shape and the semantic traps. The main residual gap is that, with zero required parameters, it never says which district is used by default or whether a district argument is effectively mandatory.

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 100%, so the schema already documents all ten parameters in detail, including formats and mutual exclusions. The description adds only a light mention of the problem and description filters and no syntax or behavior beyond the schema, which sets the correct baseline.

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 aggregation and its outputs: 'For each agency in a district and period: requests, how many are closed and not yet closed, and the median and average days to close (closed requests only).' That is a clear verb-plus-resource statement an agent can act on. It never contrasts itself with near siblings such as district_summary or problem_trend, so differentiation is left 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?

It notes the filters are optional ('Optional problem and description filters') and implicitly sets scope to a district and period, but gives no explicit when-to-use or when-not-to-use guidance against alternatives. With three overlapping date controls (from_date/to_date, last_days, fiscal_year) and two mutually exclusive district parameters, some routing guidance would have helped.

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