nyc-311-mcp

What's changed

whats_changed

Read-only

Check recent changes to NYC 311 data, site, and server, including data corrections and fixes. Use before relying on earlier figures or verifying whether an issue was fixed.

Instructions

What has changed in this server, its data and its website, newest first, from the project's WHATS-CHANGED.md: new tools and pages, new data, data fixes, and corrections when BetaNYC published something wrong. Each correction says what to re-check if you used the old numbers. Call this before relying on a figure you got from this server earlier, or when a user asks whether something was fixed. Filter with since (YYYY-MM-DD; also keeps older entries that have an update on or after that date) and tag (Site, Data, MCP or Correction).

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": "whats_changed"
  }
}

Input Schema

Name	Required	Description
`tag`	No	Only changes with this tag: Site, Data, MCP or Correction (any case; answers use these spellings). Correction lists every correction.
`limit`	No	Most entries to return (default 10, max 50)
`since`	No	Only changes on or after this date, YYYY-MM-DD

Output Schema

Name	Required	Description
`note`	Yes
`server`	Yes
`source`	Yes	Where to read the full history
`entries`	Yes
`filters`	Yes
`returned`	Yes
`history_begins`	Yes
`total_matching`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.3.0Nov 14, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the read-only and closed-world profile, so credit goes to what the description adds: entries are returned newest first, they are sourced from WHATS-CHANGED.md, and correction entries explain what to re-check if old numbers were used. Missing details are minor for a read-only feed (no pagination cursor behavior, no statement of how large the log is).

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?

Lead sentence front-loads the resource, ordering, and source file; usage guidance follows; filter mechanics come last, which is the right priority order. The middle sentence about corrections is valuable but the entry-type enumeration slightly duplicates the tag list given at the end.

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 zero-required-parameter, three-filter read tool with full schema coverage, annotations, and an output schema, the description covers purpose, ordering, source provenance, invocation triggers, and filter semantics. Nothing an agent needs to call it correctly is 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 baseline is 3, but the description genuinely adds meaning beyond the schema: the since filter 'also keeps older entries that have an update on or after that date,' which is a non-obvious interpretation the schema's plain 'on or after this date' wording does not convey. It also confirms the tag values are accepted in any case and that Correction returns every correction, both of which refine rather than restate 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?

States a specific resource and behavior: a newest-first changelog read from the project's WHATS-CHANGED.md, covering new tools/pages, new data, data fixes, and corrections. The enumeration of entry types makes it unmistakable that this is a change-history feed rather than a data query, which cleanly separates it from data-returning siblings like find_requests or district_summary.

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 two concrete invocation triggers: before relying on a figure previously obtained from this server, and when a user asks whether something was fixed. That is clear when-to-use context, but no when-not guidance or named alternative is offered for the case where the agent actually wants current data rather than the changelog.

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