Skip to main content
Glama
grants-discovery-mcp-server

grants-discovery-mcp-server

Search Past Federal Awards

grants_search_past_awards
Read-onlyIdempotent

Search historical federal grant awards on USAspending.gov to identify funded organizations, funding agencies, and typical award amounts for competitive research.

Instructions

Search historical federal grant awards on USAspending.gov to see who has been funded, by whom, and how much. Useful for competitive research: find peer organizations funded for a topic, typical award sizes, and which agencies fund an area.

Examples:

  • "Who got funded for rural diabetes programs in FY2024?" -> keyword="rural diabetes", fiscal_year_start=2024, fiscal_year_end=2024

  • "What has Navajo Nation received?" -> recipient="Navajo Nation" Results are sorted by award amount, largest first.

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": "grants_search_past_awards"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, starting at 1
limitNoResults per page
keywordNoTopic text matched against award descriptions
recipientNoRecipient name search, e.g. 'University of Michigan'
fiscal_year_endNoLast federal fiscal year
response_formatNo'markdown' for readable text, 'json' for structured datamarkdown
fiscal_year_startNoFirst federal fiscal year (Oct-Sep)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuinely new behavioral facts: the upstream data source (USAspending.gov) and the result ordering ('sorted by award amount, largest first'), which the agent cannot infer from annotations or schema. It does not mention rate limits or pagination depth, keeping 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.

Conciseness5/5

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

Front-loaded one-sentence purpose, then a short rationale, then two compact examples, then the sort rule. Every sentence carries information an agent needs, and the examples are the most efficient possible way to convey parameter usage.

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 no output schema, the description still tells the agent what comes back (funded organizations, funders, dollar amounts) and in what order, which is the key return-value information. Pagination and the markdown/json response choice are left entirely to the schema, which documents them adequately, so only minor gaps remain.

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 earns above that by demonstrating real parameter combinations (keyword + fiscal_year_start/end as a range for a topic query, recipient alone for an entity query). This shows the intended semantics of the year range and the topic vs. entity distinction better than the schema's one-line field notes.

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 and resource ('Search historical federal grant awards on USAspending.gov') and enumerates what the result answers (who funded, by whom, how much). The word 'past awards' plus 'historical' cleanly separates it from sibling searches over open opportunities.

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 an explicit use case ('competitive research: find peer organizations funded for a topic, typical award sizes, and which agencies fund an area') and two worked examples that show how a natural-language question maps to parameters. It stops short of naming when-not to use it or pointing at a specific sibling alternative, so it is strong context rather than full routing guidance.

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