The Mine Works

search_sam_gov_contracts

Search live US federal contract opportunities on SAM.gov: solicitations, presolicitations, sources-sought, and award notices. Filter by keyword, NAICS code, notice type, agency, and set-aside type. Requires your own free SAM.gov / api.data.gov API key.

Input Schema

TableJSON Schema

Name	Required	Description
`apiKey`	Yes	Your free SAM.gov / api.data.gov API key. Get one at sam.gov (Account Details -> API Key) or api.data.gov/signup.
`keyword`	No	Full-text search on the opportunity title (e.g. "software")
`postedTo`	No	Latest posted date. Defaults to today.
`naicsCode`	No	NAICS industry code, up to 6 digits (e.g. "541511")
`maxResults`	No	Max opportunities to return (default 100)
`noticeType`	No	Procurement type code: o=Solicitation, p=Presolicitation, r=Sources Sought, a=Award Notice, k=Combined Synopsis, s=Special Notice, g=Sale of Surplus, u=Justification, i=Intent to Bundle
`postedFrom`	No	Earliest posted date, MM/DD/YYYY or YYYY-MM-DD. Defaults to 30 days ago.
`setAsideType`	No	Set-aside code (e.g. "SBA", "8A", "WOSB", "HZC")
`organizationName`	No	Department/sub-tier name (e.g. "DEPARTMENT OF DEFENSE")

Schema Changelog

Changes observed during successful MCP inspections.

AddedJul 31, 2026

TDQS

A3.9/5.0

Behavior3/5

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

No annotations provided, so the description must disclose behavior. It mentions the requirement for an API key and the 'live' nature, but does not state read-only intent, rate limits, or response format. For a search tool, safety is implied, but the disclosure is not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action verb 'Search'. Includes essential information (scope, filters, API key requirement) without unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 9 parameters, no annotations, and no output schema, the description covers the core purpose and key filters but omits return format, error behavior, and clarifications (e.g., 'agency' maps to organizationName). It is sufficient for tool selection but lacks details for full invocation confidence.

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 parameters are fully described in the schema. The description reiterates some parameter names (keyword, NAICS, notice type, agency, set-aside) but adds no extra detail beyond the schema. Baseline 3 applies.

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 clearly specifies the tool's function: 'Search live US federal contract opportunities on SAM.gov' with a list of notice types. It distinguishes from sibling tools by naming SAM.gov contracts specifically, unlike generic search tools.

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 description provides clear context for when to use the tool ('Search live US federal contract opportunities'), but does not explicitly mention alternatives or exclusions. The filter capabilities (keyword, NAICS, notice type, agency, set-aside) imply relevant use cases, so it's above minimal guidance.

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

All The Mine Works tools Inspect

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

Need Help?