Skip to main content
Glama
nyc-council-mcp

nyc-council-mcp

get_bill_attachments

Retrieve attachments for a NYC Council bill or matter—committee reports, resolution text, charts, transcripts, and agendas—with direct download links. Pass a numeric matter ID; returns [] if none.

Instructions

List the files attached to a bill or other matter — committee reports, resolution text, charts, hearing transcripts, agendas — from the live Legistar API. Each row has MatterAttachmentName and MatterAttachmentHyperlink (a direct download URL). Takes the numeric matter id (MatterId from get_bill or search_legislation_live; matter_id from the local tools). Many matters have none: [] is a normal answer.

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": {
      "matter_id": "<matter_id>"
    },
    "name": "get_bill_attachments"
  }
}

Input Schema

NameRequiredDescriptionDefault
matter_idYesLegistar matter ID (MatterId / matter_id), not the file number

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.9.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the live-data source, the column names returned, that a hyperlink is a direct download URL, and that empty results are common. It omits auth/permission requirements, pagination, and rate-limit behavior, which keeps it from a 5.

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

Conciseness5/5

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

Front-loaded with the action and resource, then return shape, then id sourcing, then the empty-result caveat. No filler sentences; the file-type enumeration earns its place by calibrating expectations about what attachments look like.

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 single-parameter read tool with no output schema, the description covers purpose, id provenance, returned fields, and the empty-result case. Only pagination/volume behavior and any access constraints are left unstated, which is a minor gap.

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; the description still adds value by pointing at the exact upstream tools that supply the MatterId and re-emphasizing that it is not the file number. That routing information is not present in 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?

Specific verb plus resource ('List the files attached to a bill or other matter') with concrete examples of what a file can be, and an explicit data source (live Legistar API). An agent can immediately tell this apart from get_bill or get_bill_history, which return bill data rather than attachments.

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?

It tells the agent where the required id comes from (MatterId from get_bill or search_legislation_live; matter_id from local tools) and sets the expectation that [] is a normal answer, which prevents wasted retries. It does not state any explicit when-not condition or name a competing attachment tool, so it stops short of a 5.

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