Expiring US federal contracts MCP: recompete search by NAICS/agency. Free first 10; $29/mo.
Scored across 1 tool
With only a single tool, there is no possibility of misselection or overlap. The tool's purpose (finding soon-to-expire federal contracts likely to be re-competed) is stated clearly and unambiguously.
The lone tool follows a clear verb_noun snake_case convention (search_recompetes). With one tool there is no convention mixing, and the name is readable and self-descriptive.
One tool is thin even for a narrow lookup service: there is no way to paginate past the first 10 matches, inspect a specific contract, or refine results. It is defensible for a single-purpose radar API but borderline minimal.
Search is the core operation and is covered, but the surface lacks obvious follow-ups such as fetching details for one contract, paging beyond the first 10 rows, or filtering by agency/NAICS. Agents hit a dead end once they want more than the initial list.
Search US federal contracts ($1M+) ending within 12 months, likely to be re-competed. Returns count, total potential value and the first 10 matches (all rows with a Radar Pro key). Data: USAspending.gov.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Incumbent name contains | |
| key | No | Optional Radar Pro key: every matching row instead of the first 10 | |
| max | No | Maximum value in USD | |
| min | No | Minimum value in USD | |
| naics | Yes | NAICS codes, comma-separated (3-6 digits), e.g. 541512. Pass "" to search by agency only. | |
| state | No | Two-letter states of performance, comma-separated | |
| agency | No | Agency slugs, comma-separated (see /api/meta), e.g. department-of-defense | |
| months | No | Only contracts whose current end date is within this many months (1-12) | |
| setaside | No | Set-aside text to match, e.g. 8(a), SDVOSB, WOSB, HUBZone |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: results are truncated to the first 10 matches unless a Radar Pro key is supplied, in which case all rows are returned, and it discloses the response fields and data provenance.
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 short sentences, front-loaded with the core scope and constraints, then return shape, then data source. No filler and every sentence carries information an agent needs.
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 compensates by describing the return payload (count, total potential value, first 10 matches, or all rows with a key). Combined with 100% parameter coverage, the only minor gaps are pagination/rate-limit behavior and how the optional key is obtained.
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 coverage is 100%, so the baseline is 3, but the description reveals implicit default behavior for two parameters not stated in the schema: a $1M minimum value floor and a 12-month end-date window, which map to min and months. It also implicitly explains that key controls result-set completeness, adding meaning beyond the schema text.
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) plus a tightly bounded resource: US federal contracts over $1M ending within 12 months that are likely to be re-competed. An agent knows exactly what domain this covers and the scope constraints without opening the schema; the only missing element, sibling differentiation, is moot because no siblings exist.
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?
The description implies its use case (finding expiring contracts that will be re-competed) and names the upstream data source, USAspending.gov, but never states when to use this versus other approaches or any prerequisites. With no sibling tools there is nothing to route against, so the guidance is adequate but only implied.
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_recompetes4 fields changedInput schema / properties / agency / examplesAdded value: +[
+ "department-of-defense"
+]Input schema / properties / naics / descriptionPrevious value: -"NAICS codes, comma-separated (3-6 digits), e.g. 541512"New value: +"NAICS codes, comma-separated (3-6 digits), e.g. 541512. Pass \"\" to search by agency only."Input schema / properties / naics / examplesAdded value: +[
+ "541512"
+]Input schema / requiredAdded value: +[
+ "naics"
+]search_recompetesFederal+SLED govcon MCP: SAM, USASpending, recompete, hearings, policy intel, search. Private AI.
US federal contracts: solicitations, set-asides, deadlines, awards, contractor profiles. Free.
Predict federal contract recompetes: expiring contracts, likely competitors, win odds.
Federal sales intelligence: expiring-contract triggers, agency spend intel, deal qualification.
Add one secure layer between your agents and this server.
