US federal contract and grant awards: who won, amounts, agencies (USAspending.gov). x402.
Scored across 1 tool
There is only one tool, so there is no possibility of misselection or overlap with any sibling tool. Its purpose (keyword/recipient/agency/NAICS award search) is stated explicitly and unambiguously.
The single name follows a clean, predictable verb_noun convention (search_us_federal_awards) with snake_case throughout. There are no competing conventions to conflict with it.
A single search tool is thin for a whole federal-award domain that also involves detail lookups, recipient profiles and agency breakdowns. It works as a focused endpoint, but the surface feels under-provisioned rather than well-scoped.
Search covers the core use case (who won what, by keyword/recipient/agency/NAICS/date) and returns a rich field set, but there is no award-detail-by-ID, recipient lookup, or spending-aggregation operation. Agents cannot drill into a specific award or compare recipients without re-running searches.
Search US federal awards from USAspending.gov (official Treasury data): contracts, IDVs, grants or loans by keyword, recipient name, awarding agency, NAICS and date range. Returns award ID, recipient, UEI, amount, agency, sub-agency, dates, description, place of performance and links. Use when you need to know who wins US federal contracts or grants (competitors, partners, sales leads) or what a given company has been awarded, by keyword, recipient, agency, NAICS or date. Paid per call via x402 (USDC on Base).
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Look-back days (default 365) | |
| limit | No | Max results (default 20) | |
| naics | No | NAICS codes | |
| query | No | Keywords | |
| agency | No | Awarding agency | |
| recipient | No | Recipient name | |
| award_type | No | Default contracts | |
| payment_signature | No | x402 v2 PAYMENT-SIGNATURE header value. Omit to receive payment requirements. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden, and it delivers the single most important behavioral fact: the tool is 'Paid per call via x402 (USDC on Base)', with the schema explaining that omitting payment_signature returns payment requirements. It also discloses the returned field set. It does not mention rate limits, latency, or pagination beyond the limit parameter.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with what it does and where the data comes from, followed by return fields, then usage context, then the payment model. Dense but every sentence carries information; the return-field list is the only part that could be trimmed slightly since no output schema exists to carry it.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description usefully enumerates the return fields (award ID, recipient, UEI, amount, agency, dates, place of performance, links). The commercial model (x402/USDC payment) is disclosed, which an agent needs before calling. Minor gaps remain around result ordering, pagination, and error/auth behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 8 parameters is already documented in the schema, including defaults (365 days, 20 results), the award_type enum, and payment_signature usage. The description's enumeration of keyword/recipient/agency/NAICS/date mirrors the schema rather than adding syntax or format guidance, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (search) and resource (US federal awards) plus the authoritative source (USAspending.gov, official Treasury data) and the concrete award types covered (contracts, IDVs, grants, loans). An agent immediately knows what this 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides an explicit use context: 'Use when you need to know who wins US federal contracts or grants (competitors, partners, sales leads) or what a given company has been awarded.' It also enumerates the filterable dimensions. There are no sibling tools, so no exclusions to state, but it stops short of saying when NOT to use it (e.g. non-US or state-level awards).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search_us_federal_awardsUS federal contracts, grants, and spending awards
US federal contracts: solicitations, set-asides, deadlines, awards, contractor profiles. Free.
Who won EU public contracts: winners, values, buyers and CPV from TED award notices. Paid via x402.
SAM.gov contracts and USAspending awards. 4 procurement tools.
Add one secure layer between your agents and this server.
