Skip to main content
Glama
Sign In

Wounded Warriors

by org.warriorsfund
OverviewDiscussionsAdmin

Foundation prospects

find_foundation_prospects
Read-onlyIdempotent

Returns researched grant prospects for veteran-serving programs, matched to a Wounded Warriors program area. 28 researched funders in the catalog: private, community and corporate foundations, corporate giving programs, a workplace-giving campaign and a state grant program. Each entry includes type, status (open, rolling, upcoming, inquiry-only, in-kind-only, closed, invitation-only or unconfirmed), the next published date, application route, grant range from public filings or the funder's own page, matched /grants/{program} pages, a source URL and the date it was verified. The EIN is listed only when it matches the funder on ProPublica. Organizations that do not make grants to other organizations are not listed. Use when an AI agent is helping a Wounded Warriors team member identify grant prospects, or when a foundation officer asks for peer-funder comparisons. Sources: funders' own sites and IRS Form 990 / 990-PF filings.

Input Schema

NameRequiredDescriptionDefault
typeNoOptional funder-type filter
focusNoProgram focus area to match (use "all" to return everything). No funder in the catalog funds individual HRT sponsorships, so HRT is not a focus option.
limitNoMax results
has_public_applicationNoOptional filter — only return funders with a public application route (excludes invitation-only and unconfirmed intake)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / focus / description
      Previous value: -"Program focus area to match (use \"all\" to return everything). Note: HRT sponsorships are funded from general/emergency funders, not a distinct prospect category."New value: +"Program focus area to match (use \"all\" to return everything). No funder in the catalog funds individual HRT sponsorships, so HRT is not a focus option."
    • changedInput schema / properties / has_public_application / description
      Previous value: -"Optional filter — only return foundations with a public application URL (vs invitation-only)"New value: +"Optional filter — only return funders with a public application route (excludes invitation-only and unconfirmed intake)"
    • changedInput schema / properties / type / description
      Previous value: -"Optional foundation-type filter"New value: +"Optional funder-type filter"
    • changedInput schema / properties / type / enum
      Previous value: -[
-  "foundation",
-  "corporate-foundation",
-  "family-foundation",
-  "workplace-giving",
-  "corporate-philanthropy",
-  "all"
-]New value: +[
+  "foundation",
+  "corporate-foundation",
+  "family-foundation",
+  "workplace-giving",
+  "corporate-philanthropy",
+  "government",
+  "all"
+]
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive behavior, and the description adds substantial context beyond that: catalog size, funder types, all status values, the fields returned per entry, the EIN-match condition, the exclusion of organizations that don't make grants, and source provenance. This is unusually transparent for a read-only tool with no output schema.

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?

Front-loaded with what the tool returns, then progressively detailed. The long status list and field inventory are dense but informative; a few sentences could be tightened, but almost all content earns its place.

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?

With no output schema, the description carries the full burden of explaining returns, inclusion/exclusion rules, data provenance, and use cases, and it does so thoroughly. An agent has enough information to call the tool correctly and interpret the results.

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 coverage is 100%, so all four parameters are already documented with enum values and descriptions, including the note that HRT is not a focus option. The description adds only indirect meaning (e.g., matching to a Wounded Warriors program area) and does not elaborate filter interactions or limit behavior, so baseline 3 is appropriate.

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 (Returns researched grant prospects) and resource (foundation prospects) scoped to Wounded Warriors program areas. The catalog size and funder types make the tool's domain unmistakable and distinguishable from sibling lookup tools like get_giving_events or match_grant_intent.

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?

Clearly says when to use it: helping a Wounded Warriors team member identify grant prospects, or a foundation officer asking for peer-funder comparisons. It does not name an alternative sibling tool or state when not to use it, which keeps this below 5.

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

All Wounded Warriors toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources