Skip to main content
Glama

Sbir

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Sbir Search Awards

sbir_search_awards
Read-onlyIdempotent

"Which companies won NASA SBIR Phase II awards for autonomy?" / "SBIR awards for [topic]" / "who received DoD SBIR funding" / "Phase I and Phase II awards at [agency]" — AWARDED federal Small Business Innovation Research (SBIR) and STTR grants: the small-business R&D contracts an agency has already funded. Search by keyword, agency ("DOD", "NASA", "DARPA", "NSF", "DOE", "HHS"), year, company, or state. Returns the winning company, award amount, agency and branch, topic code, abstract, fiscal year, and Phase (I/II/III), live from www.sbir.gov/awards (219,000+ awards, 1983-present). This is the tool for who WON federal small-business R&D money and how much; for opportunities still open to bid use sbir_search_solicitations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoFilter by award year (e.g., 2024)
limitNoNumber of results to return (default 20, max 100). Award amounts and other detail-page fields are only fetched for the first 25 rows (a bounded number of extra HTTP calls); rows beyond that carry list-level fields only and `enriched: false`.
stateNoFilter by 2-letter US state code (e.g., "CA", "MA") — sent as sbir.gov's own state filter.
agencyNoFilter by funding agency: DOD, HHS, NASA, NSF, DOE, USDA, EPA, DOC, ED, DOT, DHS, NIH, DARPA, ARMY, NAVY, USAF, and others sbir.gov itself lists. "DOW" is also accepted and translated to "DOD" — sbir.gov's own form still uses "DOD".
companyNoFilter by company name (substring match against sbir.gov's own company_name filter — a partial name like "Rydberg" matches "RYDBERG TECHNOLOGIES INC").
keywordNoSearch term to match against award titles and abstracts.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesNumber of awards returned
awardsYes
keywordYesSearch keyword used

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "agency": "DOW",
-    "keyword": "machine learning",
-    "limit": 20,
-    "year": 2024
-  },
-  {
-    "keyword": "renewable energy",
-    "limit": 50,
-    "state": "CA"
-  }
-]New value: +[
+  {
+    "keyword": "liquid biopsy",
+    "limit": 5
+  },
+  {
+    "keyword": "quantum sensing",
+    "limit": 5
+  }
+]
    • changedInput schema / properties / agency / description
      Previous value: -"Filter by funding agency: DOW (Department of War, formerly DOD — \"DOD\" is accepted and translated), HHS, NASA, NSF, DOE, USDA, EPA, DOC, ED, DOT, DHS."New value: +"Filter by funding agency: DOD, HHS, NASA, NSF, DOE, USDA, EPA, DOC, ED, DOT, DHS, NIH, DARPA, ARMY, NAVY, USAF, and others sbir.gov itself lists. \"DOW\" is also accepted and translated to \"DOD\" — sbir.gov's own form still uses \"DOD\"."
    • changedInput schema / properties / company / description
      Previous value: -"Filter by company name"New value: +"Filter by company name (substring match against sbir.gov's own company_name filter — a partial name like \"Rydberg\" matches \"RYDBERG TECHNOLOGIES INC\")."
    • changedInput schema / properties / keyword / description
      Previous value: -"Search term to match against award titles, abstracts, and topics"New value: +"Search term to match against award titles and abstracts."
    • changedInput schema / properties / limit / description
      Previous value: -"Number of results to return (default 20, max 100)"New value: +"Number of results to return (default 20, max 100). Award amounts and other detail-page fields are only fetched for the first 25 rows (a bounded number of extra HTTP calls); rows beyond that carry list-level fields only and `enriched: false`."
    • changedInput schema / properties / state / description
      Previous value: -"Filter by 2-letter US state code (e.g., \"CA\", \"MA\")"New value: +"Filter by 2-letter US state code (e.g., \"CA\", \"MA\") — sent as sbir.gov's own state filter."
  2. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
-  "keyword"
-]New value: +[]
  3. Changed2 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "agency": "DOD",
-    "keyword": "machine learning",
-    "limit": 20,
-    "year": 2024
-  },
-  {
-    "keyword": "renewable energy",
-    "limit": 50,
-    "state": "CA"
-  }
-]New value: +[
+  {
+    "agency": "DOW",
+    "keyword": "machine learning",
+    "limit": 20,
+    "year": 2024
+  },
+  {
+    "keyword": "renewable energy",
+    "limit": 50,
+    "state": "CA"
+  }
+]
    • changedInput schema / properties / agency / description
      Previous value: -"Filter by funding agency (e.g., \"DOD\", \"HHS\", \"NASA\", \"NSF\", \"DOE\", \"USDA\")"New value: +"Filter by funding agency: DOW (Department of War, formerly DOD — \"DOD\" is accepted and translated), HHS, NASA, NSF, DOE, USDA, EPA, DOC, ED, DOT, DHS."
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "awards": {
+      "items": {
+        "properties": {
+          "abstract": {
+            "description": "Award abstract or summary",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "agency": {
+            "description": "Funding agency code",
+            "type": "string"
+          },
+          "award_amount": {
+            "description": "Award amount in dollars",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "award_id": {
+            "description": "Unique award identifier",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "award_title": {
+            "description": "Title of the award",
+            "type": "string"
+          },
+          "award_year": {
+            "description": "Year award was made",
+            "type": [
+              "number",
+              "string",
+              "null"
+            ]
+          },
+          "branch": {
+            "description": "Agency branch or division",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "city": {
+            "description": "City location",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "company": {
+            "description": "Company name",
+            "type": "string"
+          },
+          "phase": {
+            "description": "Funding phase (Phase I, Phase II, etc.)",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "program": {
+            "description": "SBIR/STTR program type",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "state": {
+            "description": "2-letter state code",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "topic_code": {
+            "description": "Topic or program code",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "company",
+          "agency",
+          "award_title"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "count": {
+      "description": "Number of awards returned",
+      "type": "number"
+    },
+    "keyword": {
+      "description": "Search keyword used",
+      "type": "string"
+    }
+  },
+  "required": [
+    "keyword",
+    "count",
+    "awards"
+  ],
+  "type": "object"
+}
  5. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "agency": "DOD",
+    "keyword": "machine learning",
+    "limit": 20,
+    "year": 2024
+  },
+  {
+    "keyword": "renewable energy",
+    "limit": 50,
+    "state": "CA"
+  }
+]
  6. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive). The description adds genuinely useful context beyond them: the live data source (www.sbir.gov/awards), dataset size (219,000+ awards, 1983-present), and confirmed-awarded scope. It does not mention rate limits or pagination behavior, so it is strong but not exhaustive.

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 intent-matching example queries and then a dense, well-organized single paragraph. It is slightly long with multiple quoted phrasings, but each clause earns its place by mapping user phrasing to the tool.

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?

For a 6-parameter open-world search with annotations and an output schema, the definition is essentially complete: it covers scope, data source, filters, and sibling disambiguation. Listing return fields is mildly redundant given the output schema exists, but harmless.

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 all six parameters, including the limit/enrichment caveat. The description restates the filter dimensions (keyword, agency, year, company, state) but adds no syntax or format detail the schema lacks. 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?

The description states a specific verb and resource (search AWARDED federal SBIR/STTR grants) and immediately scopes it against the sibling: 'the tool for who WON federal small-business R&D money... for opportunities still open to bid use sbir_search_solicitations.' An agent can route correctly without opening 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 Guidelines5/5

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

It provides explicit when-to-use framing via quoted example questions, lists the queryable dimensions, and names the alternative tool with the exact condition that selects it (won vs. still open). No inference required.

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

All Sbir 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