Skip to main content
Glama

Forecast Search

forecast_search
Read-onlyIdempotent

Search US federal agency PROCUREMENT FORECASTS, contracts an agency has published its intention to award in a future fiscal year, months to years before any solicitation exists. Answers "what is DHS planning to buy next year", "upcoming IT services opportunities FY27", "planned acquisitions in my NAICS", "future set-aside work for small business". Each result carries the requirement title and description, NAICS, estimated value band, small-business set-aside, anticipated award quarter, contracting office and a named point of contact. This is the DEMAND side and it is forward-looking: for contracts already awarded use USASpending, and for solicitations already open for bid use the govcon tools. Currently covers the Department of Homeland Security and its components (CBP, ICE, TSA, FEMA, USCG, USCIS, USSS, CISA, FLETC), call forecast_agencies for exactly what is wired and why. Keyless.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "naics": "5415",
      "agency": "DHS"
    },
    "name": "forecast_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax rows, 1-100 (default 20). `total_matches` reports the full count regardless.
naicsNoNAICS code, matched as a PREFIX so "5415" covers 541511/541512/etc. Also accepts a full 6-digit code.
agencyNoAgency key, e.g. "DHS". Omit for all wired agencies. See forecast_agencies.
keywordNoFree text matched against the requirement title and description, e.g. "cloud", "training", "body armor", "case management".
min_valueNoMinimum estimated value in USD, compared against the TOP of each band so a "$10M to $20M" row matches min_value 15000000.
set_asideNoSmall-business program: "8(a)", "SB", "SDVOSB", "HUBZone", "WOSB", "AbilityOne", "None", "TBD".
sub_agencyNoDHS component or office, matched as a prefix of the organization path, e.g. "CBP", "TSA/OIT", "USCG".
fiscal_yearNoFederal fiscal year of the planned award, e.g. 2027.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Max rows, 1–100 (default 20). `total_matches` reports the full count regardless."New value: +"Max rows, 1-100 (default 20). `total_matches` reports the full count regardless."
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered; the description adds genuinely useful context beyond them by naming the data scope limit (DHS components only), the 'Keyless' auth posture, and the shape of each returned row. It does not discuss result volume or pagination, though the limit/total_matches parameters partially cover that in schema.

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?

Front-loads what the tool is and the forward-looking framing before the coverage caveat and the sibling routing. Every sentence carries distinct information: definition, example intents, return fields, boundary, coverage, auth — no filler.

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?

For an 8-parameter, optional-only tool with no output schema, the description compensates well by enumerating the fields each result carries (title, description, NAICS, value band, set-aside, award quarter, office, contact) and by stating coverage limits. It is essentially complete, with only mild gaps around result volume and pagination behavior.

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 every one of the eight parameters is already documented with formats and matching behavior. The description reinforces intent (NAICS, set-aside, fiscal year, value band) through its example queries but adds no parameter detail the schema lacks, making the baseline 3 appropriate.

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 ('Search US federal agency PROCUREMENT FORECASTS') and then defines the resource precisely as contracts an agency intends to award months to years before solicitation. It explicitly separates itself from USASpending (awarded contracts) and the govcon tools (open solicitations), so an agent can pick it without opening any schema.

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?

Gives concrete when-to-use phrasings ('what is DHS planning to buy next year', 'upcoming IT services opportunities FY27') plus explicit when-not-to-use routing to USASpending and govcon tools. It also states the current coverage boundary (DHS and named components) and points at forecast_agencies for the authoritative list.

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.