Skip to main content
Glama

Follow new federal grants to state and local governments

follow_the_grant
Read-onlyIdempotent

New federal project grants and cooperative agreements to state and local governments (USAspending assistance awards), largest first: the government, the program, the purpose, the dollars obligated, and where that government posts its bids (its entry in SpendQuery's bid-portal directory: portal, open-bids list, vendor registration) when the name matches a listed state, county or city. Use it for "which cities near me just won federal money for X": the government usually buys the work itself, later, on its own portal. A grant is a sign, not a solicitation; say so, and send the user to the portal to look for the bid.

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": "follow_the_grant"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoWords in the grant's purpose, program or recipient, e.g. "runway" or "water".
daysNoGrants made in the last 30, 90, 180 or 365 days of loaded data (default 90).
levelNoOnly this kind of government.
limitNoHow many grants to return, 1-50 (default 20).
stateNoA 2-letter state code, e.g. "KS".
min_amountNoSmallest grant in dollars: 250000, 1000000 (default), 5000000 or 25000000.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the readOnly/idempotent/non-destructive annotations it discloses the enrichment rule: portal details are attached only when the recipient name matches a listed state, county or city in SpendQuery's directory — a real failure mode an agent would otherwise misread as missing data. It also warns the agent to frame results as a sign, not a solicitation, which is behavioral guidance annotations cannot carry.

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 essential scoping and the 'not a solicitation' caveat are front-loaded, and each sentence carries information. The opening sentence is overloaded with nested parentheticals ('its entry in SpendQuery's bid-portal directory: portal, open-bids list, vendor registration'), which slows parsing but is not wasteful.

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?

With 100% schema coverage, annotations and an output schema, the description need only cover intent, the enrichment caveat and interpretation — all present. It omits any note on what happens when the recipient does not match the directory (portal fields null?) and never contrasts with sibling award/bid tools, which a 6-param tool of this shape could afford.

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 all six parameters (q, days, level, limit, state, min_amount) are already documented with examples and defaults. The description adds only the largest-first sort order and the name-matching condition behind the portal enrichment; it adds no format or semantics beyond 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 verb+resource (new federal project grants and cooperative agreements to state and local governments, from USAspending assistance awards) plus the ordering (largest first). The final clause — 'A grant is a sign, not a solicitation' — explicitly separates it from grant_opportunities-style tools that return solicitations.

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 a concrete trigger phrase ('which cities near me just won federal money for X') and the downstream workflow (government buys the work later on its own portal). It implies but never names alternatives such as grant_opportunities or search_local_bids, so routing is inferential rather than explicit.

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