Skip to main content
Glama

Search state and local bids and contracts

search_local_bids
Read-onlyIdempotent

State, county and city government bids and contracts (not federal awards), from the governments that publish them as open data: Los Angeles (the City, LA County, LADWP, LAUSD, airports, port, Metro), New York City, San Francisco, Washington DC, Chicago, Cook County, Austin, Detroit, Richmond, Sacramento, Baton Rouge, Montgomery County MD, Delaware, Texas DOT, California state departments (Cal eProcure), SUNY construction, E-Rate and others. kind: "open" (taking responses, soonest due first), "planned" (forecasts: TxDOT's planned lettings, Illinois CDB, San Diego County), "awarded" (contracts first awarded in the last year: who won, net amounts) or "current" (in force today, soonest ending first: the re-bids). q: words in the title or description; state: two-letter code (open and planned bids); source: one source key from the reply's sources. Coverage is partial: no tool has every state, county and city; say so when the place asked about isn't covered. Each row links to the government's own record (source_url).

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": "search_local_bids"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoWords in the title or description, e.g. "roofing" or "janitorial".
kindNoopen (taking responses, soonest due first), planned (forecasts), awarded (contracts first awarded in the last year) or current (in force today, soonest ending first).open
limitNoMost rows to return, 1-50.
stateNoTwo-letter state code, e.g. "TX" (open and planned bids).
sourceNoOne source key from the reply's sources, e.g. "txdot", "nyc", "lacity".

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "title": "search_local_bidsDictOutput",
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world, so the description's job is additive – and it does add: per-kind sort order (soonest due first, soonest ending first), the fact that each row carries source_url to the government's own record, and an explicit warning that coverage is partial. It does not discuss result volume, rate limits, or freshness lag, which keeps it off 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.

Conciseness4/5

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

Purpose and the federal exclusion are front-loaded, and the kind semantics follow in a compact one-line list. The long parenthetical roll-call of agencies (LADWP, LAUSD, airports, port, Metro, Cal eProcure, SUNY, E-Rate...) is bulky, though it does double as coverage evidence for an agent judging whether a locality is supported.

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?

Five optional parameters, a rich output schema and full annotation coverage mean the description only needs to supply scope, sort behavior and coverage limits – and it supplies all three, plus the source_url provenance note. Nothing an agent needs before calling is missing.

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 q, kind, limit, state and source, including the enum semantics the description repeats nearly verbatim. The description adds only two smaller points: that state applies to open and planned bids, and that source keys come from the reply's sources list. Baseline 3 is correct here.

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?

Opens with a specific resource and scope: "State, county and city government bids and contracts (not federal awards)", and immediately narrows to governments that publish open data, naming concrete sources. An agent can distinguish this from the federal-flavored siblings (search_far, search_notices) without reading either schema.

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 real selection guidance for the `kind` enum (open = taking responses soonest due first; planned = forecasts; awarded = last year's awards; current = in force today) and states the exclusion for federal awards. It also tells the agent how to behave when coverage misses ("say so when the place asked about isn't covered"). It stops short of naming sibling tools to redirect to for non-covered geographies or federal data.

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