SpendQuery

Search open contract notices

search_notices

Read-onlyIdempotent

Open SAM.gov contract notices still taking responses, in one call (no QueryPlan): by words (also matched by meaning), NAICS, place, set-aside, agency and notice type, soonest deadline first. Each notice has its id (for get_notice), set-aside, deadline with time zone, days left, the stated or likely size, a single-bid risk flag and its SAM.gov link; with counts by notice type and set-aside. near + miles: only work within that many miles of a ZIP, city or county (each notice then has miles; notices that name only a state are left out: say so). For past awards and money use run_plan.

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": "search_notices"
  }
}

Input Schema

Name	Required	Description	Default
`q`	No	Words for the work, e.g. "janitorial" or "cloud migration" (matched by meaning too).
`days`	No	Responses due within this many days, 1-365 (default 60).
`near`	No	Work within `miles` of a ZIP code, city or county, e.g. "93065", "Los Angeles, CA".
`sort`	No	due (soonest deadline first), posted (newest first) or size.	due
`limit`	No	How many notices to return, 1-50 (default 20).
`miles`	No	The radius for `near`, 1-200 miles (default 25).
`naics`	No	A NAICS code or industry words, e.g. "561720" or "IT services".
`state`	No	Place of performance: a state code or name, e.g. "VA" or "Texas".
`agency`	No	A department, bureau or office, e.g. "Navy", "VA", "Department of Energy".
`set_aside`	No	A set-aside as people say it, e.g. "SDVOSB", "8(a)", "small business", "HUBZone".
`notice_type`	No	A notice type, e.g. "Solicitation", "Sources Sought", "Combined Synopsis/Solicitation".

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 6, 2026

addedInput schema / properties / miles

Added value: +{
+  "default": 25,
+  "description": "The radius for `near`, 1-200 miles (default 25).",
+  "title": "Miles",
+  "type": "number"
+}

addedInput schema / properties / near

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Work within `miles` of a ZIP code, city or county, e.g. \"93065\", \"Los Angeles, CA\".",
+  "title": "Near"
+}

Changed1 schema field changedNov 5, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "search_noticesDictOutput",
+  "type": "object"
+}

AddedNov 5, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's job is the operational detail, and it delivers: default deadline ordering, counts by notice type and set-aside, and the notable edge case that with near + miles, notices naming only a state are excluded and the agent should say so. That exclusion rule is real behavior an agent could not infer from annotations or schema; the enumerated return fields are partly redundant with the output schema.

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 the core purpose and the no-QueryPlan differentiator, then the output shape, then the geo filter, with the run_plan redirect last. It is dense but each clause carries information; the main waste is the long enumeration of returned fields when an output schema already defines them.

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?

With 11 optional parameters, 100% schema coverage, an output schema, and annotations, the description covers what remains: ordering, geo-filter caveats, and where to go for awards. The only soft spot is the unexplained instruction-like 'say so' tied to the state-only exclusion, which could be phrased more precisely, but an agent can still call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3 and the schema already explains each parameter individually with examples. The description adds meaning the schema cannot: that the word query is also matched semantically, and critically that near and miles act as a joint filter that stamps a `miles` value on each notice. That interaction semantics is genuine added value.

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?

States a specific verb and resource — open SAM.gov contract notices still accepting responses — plus the immediate scope qualifier 'in one call (no QueryPlan)'. That qualifier alone separates it from the planning sibling run_plan, and the parenthetical reference to get_notice marks the follow-up path.

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?

Explicitly routes away: 'For past awards and money use run_plan,' which names both the excluded use case and the alternative tool. It also signals the contrast with QueryPlan-based flows and defers detail lookups to get_notice, so the agent knows when this tool is and is not the right entry point.

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

All SpendQuery 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?