Skip to main content
Glama

Search SBIR and STTR awards

sbir_awards
Read-onlyIdempotent

SBIR and STTR awards since 1983 from SBA's SBIR.gov records, and who received them: totals, awards by year (Phase I / II), by agency, the companies with the most, and the latest awards (company, title, agency, phase, amount, year). Filters: agency (as SBIR.gov names it, e.g. "Department of Defense"), phase ("Phase I" or "Phase II"), program ("SBIR" or "STTR"), state (the winner's), q (words in the award title), company_uei, since (first award year). open_topics: also the SBIR/STTR solicitations open now (SAM.gov and Grants.gov). SBIR.gov counts awards by award year; USAspending (run_plan) counts money by fiscal year, so the two differ.

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": "sbir_awards"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoWords in the award title, e.g. "hypersonic" or "battery".
phaseNoThe award phase: Phase I or Phase II.
sinceNoFirst award year to count, e.g. 2020.
stateNoThe winner's two-letter state code, e.g. "VA".
agencyNoThe awarding agency as SBIR.gov names it, e.g. "Department of Defense", "National Science Foundation".
programNoThe program: SBIR or STTR.
company_ueiNoA winner's 12-character UEI, e.g. "ZFN2JJXBLZT3".
open_topicsNoAlso list the SBIR/STTR solicitations open now (SAM.gov and Grants.gov).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "title": "sbir_awardsDictOutput",
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover safety (readOnlyHint, idempotentHint, non-destructive), so the description's job is context — and it delivers: upstream data sources (SBIR.gov, plus SAM.gov/Grants.gov when open_topics is set), historical coverage since 1983, and the critical counting caveat about award year vs fiscal year. It does not mention result size limits or pagination, which is the one remaining behavioral gap.

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-loads what the tool returns, then the filter set, then the open_topics mode, then the cross-tool caveat — a sensible ordering. The filter parenthetical is dense but every clause carries information; only minor trimming would be possible without losing semantics.

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 an output schema present the description needn't spell out return shape, and it doesn't waste effort there. It covers sources, time coverage, filter vocabulary, the optional open_topics mode, and the year-basis discrepancy against the sibling spending tool — everything an agent needs to call this correctly.

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%, and the description largely restates those same descriptions (q = words in the award title, phase = Phase I/II, state = winner's state, company_uei = 12-character UEI). The only added value is that filters can be combined to shape the returned breakdowns. Baseline 3 is appropriate when the schema already documents every parameter.

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?

Names a specific resource (SBIR/STTR awards since 1983 from SBA's SBIR.gov records) and enumerates exactly what comes back: totals, awards by year/phase/agency, top companies, and latest awards with field list. It also states the filter vocabulary, so an agent knows precisely what the tool retrieves without opening the schema.

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?

The closing sentence explicitly contrasts this tool with run_plan (SBIR.gov counts by award year; USAspending counts by fiscal year), which is a real routing hint. The open_topics flag is described as an additive mode. It stops short of an explicit 'use this when…, use run_plan when…' statement, so the agent must infer the selection rule.

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