Skip to main content
Glama

Search grants

search_grants
Read-only

Search the public GrantCue grant catalog (federal, state, local and foundation opportunities) with the same filters as the Discover page. Returns a short page of matches, at most 25, and can reach the first 100 results of a search. Grant text is provided by the funders.

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_grants"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNorelevance = best match for the query, due_soon = closing soonest, newest = most recently opened. Default: relevance when there is a query, otherwise due_soon.
queryNoKeywords, an opportunity number, or a quoted phrase.
agencyNoFunding agency or organization (partial match).
offsetNoSkip this many results, to page through. Only the first 100 results of a search can be reached.
statusNoposted = open for applications now, forecasted = announced but not yet open. Default: both.
categoryNoFunding category.
locationNoA place page slug such as "allegheny-county-pa" to limit results to grants open there.
page_sizeNoResults per page. Default 10.
due_in_daysNoOnly grants closing within this many days.
max_fundingNoLargest award or total, in US dollars.
min_fundingNoSmallest award or total, in US dollars.
applicant_typeNoWho is applying. Grants that exclude this kind of applicant are left out.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / category / enum
      Previous value: -[
      -  "Agriculture",
      -  "Arts",
      -  "Business and Commerce",
      -  "Community Development",
      -  "Education",
      -  "Employment, Labor, and Training",
      -  "Energy",
      -  "Environment",
      -  "Food and Nutrition",
      -  "Health",
      -  "Housing",
      -  "Humanities",
      -  "Income Security and Social Services",
      -  "Law, Justice, and Legal Services",
      -  "Natural Resources",
      -  "Science and Technology",
      -  "Transportation",
      -  "Other"
      -]New value: +[
      +  "Agriculture",
      +  "Arts",
      +  "Business and Commerce",
      +  "Community Development",
      +  "Disaster Prevention and Relief",
      +  "Education",
      +  "Employment, Labor, and Training",
      +  "Energy",
      +  "Environment",
      +  "Food and Nutrition",
      +  "Health",
      +  "Housing",
      +  "Humanities",
      +  "Income Security and Social Services",
      +  "Law, Justice, and Legal Services",
      +  "Natural Resources",
      +  "Science and Technology",
      +  "Transportation",
      +  "Other"
      +]
  2. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and corpus boundary are covered; the description adds genuinely new behavioral facts beyond them: a hard 25-per-page cap, a 100-result reachability ceiling, and the caveat that grant text comes from funders (accuracy/source disclaimer). It stops short of describing total-count behavior or whether early results are stable across sorts.

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?

Three short sentences, front-loaded with what is searched before the result-shape and paging facts. The funder-sourced-text disclaimer is the only borderline sentence, though it does carry transparency value rather than repeating structured data.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With twelve optional filters and no output schema, the description should say more about the shape of a returned match than 'a short page of matches.' It covers result volume and reachability well, but an agent still cannot tell what fields a match contains or whether a total-match count is returned.

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 every one of the twelve parameters, including enum meanings and defaults, is already documented in the schema. The description adds no syntax or interaction detail beyond that baseline, so a 3 is the correct ceiling.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource (search the public GrantCue grant catalog) and scopes the corpus to federal, state, local and foundation opportunities. It does not explicitly distinguish itself from siblings such as search_funders or get_grant, so an agent must infer that this one returns matches rather than funder records or a single grant.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Saying it uses 'the same filters as the Discover page' gives some context, and the paging constraints (max 25 per page, first 100 results reachable) implicitly tell the agent when to page versus re-query. There is no explicit guidance on when to prefer this over search_funders or get_grant, and no stated prerequisite for narrowing a query.

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