Skip to main content
Glama

Ams Market Report

ams_market_report
Read-onlyIdempotent

Read dated rows from one USDA AMS My Market News report (fruit and vegetable shipping-point / terminal / import-crossing prices, grain, hay, cotton and other non-livestock reports). Every row keeps AMS's own fields: commodity, variety, package or unit, origin, and low / high / mostly / mean price as separate values; nothing is averaged. Optional commodity keeps only rows whose commodity, variety or group contains that word (e.g. "lime"); optional district keeps rows whose district or market location contains that text (e.g. "mexico crossings through texas"). If the report has rows but none match, the result says so and lists the commodities or districts it does carry. Reports are daily: a weekly view is a start_date/end_date range of up to 31 days, newest first. With no dates it returns the most recent report date (looking back up to a week). If AMS has no rows the status is "no_rows_for_request" with the report's last published date, never an empty array. Dates are ISO (2026-10-22).

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": {
      "limit": 20,
      "district": "mexico crossings through texas",
      "end_date": "2026-10-23",
      "commodity": "lime",
      "report_id": 2402,
      "start_date": "2026-10-19"
    },
    "name": "ams_market_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoOne report date, ISO YYYY-MM-DD.
limitNoMax rows (default 100, max 500). Newest first.
_apiKeyNoOptional. The gateway supplies the platform My Market News key; pass your own only to override.
sectionNoReport section name, case-insensitive. Omit to read the data sections (header sections are skipped).
districtNoKeep only rows whose district or market location contains this text, e.g. "mexico crossings through texas" or "mcallen".
end_dateNoRange end, ISO.
commodityNoKeep only rows whose commodity / variety / group contains this word, e.g. "lime".
report_idYesReport id from ams_market_report_search.
start_dateNoRange start, ISO (use with end_date).

Output Schema

NameRequiredDescriptionDefault
rowsNo
reportNo
sourceYes
statusYesok, no_match, no_rows_for_request or no_rows_for_commodity
messageNo
completeNo
returnedNo
commodityNo
report_idNo
requestedNo
row_countNo
truncatedNo
unit_noteNo
data_as_ofNo
price_noteNo
report_slugNo
report_titleNo
rows_with_priceNo
commodity_filterNo
sections_returnedNo
rows_without_priceNo
sections_availableNo
commodities_in_reportNo
report_last_publishedNo
report_dates_in_resultNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "commodity": "lime",
      -    "district": "mexico crossings through texas",
      -    "end_date": "2026-10-23",
      -    "limit": 20,
      -    "report_id": 2402,
      -    "start_date": "2026-10-19"
      -  }
      -]New value: +[
      +  {
      +    "commodity": "lime",
      +    "district": "mexico crossings through texas",
      +    "end_date": "2026-10-23",
      +    "limit": 20,
      +    "report_id": 2402,
      +    "start_date": "2026-10-19"
      +  },
      +  {
      +    "commodity": "corn",
      +    "limit": 10,
      +    "report_id": 2711
      +  }
      +]
  2. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description still adds substantial non-structured behavior: prices are never averaged, filtering is substring-based over several fields, a filter miss reports the commodities/districts actually present, and an empty AMS result yields status "no_rows_for_request" with the last published date rather than an empty array. That last point is exactly the kind of contract an agent cannot infer from annotations.

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?

Every sentence carries operational information — fields preserved, filter semantics, no-match behavior, date-range limits, no-date default, ISO format — with no filler or restatement of the title. It is a single dense block, though, and would read faster with the fallback and date rules broken out separately.

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

Completeness5/5

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

For a 9-parameter, open-world read tool with an output schema, the description covers everything needed to call it correctly: report identification, date vs. range semantics, filter behavior, row caps deferred to schema, and the no-rows and no-match outcomes. Return-value shape is rightly left to the output schema, so nothing material is missing.

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; the description earns an extra point by explaining parameter interactions the schema states only piecemeal. It clarifies that `date` is a single day while start_date/end_date form a range capped at 31 days with newest-first ordering, and it gives matching examples for `commodity` and `district` ("lime", "mexico crossings through texas") that show the fields a filter actually matches against.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource: "Read dated rows from one USDA AMS My Market News report," and enumerates the covered report families (shipping-point/terminal/import-crossing produce, grain, hay, cotton, non-livestock). An agent knows exactly what data comes back. It never explicitly contrasts itself with the similarly named siblings ams_report and ams_report_search, so it stops short of a 5.

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?

Gives concrete usage context: daily cadence, weekly views expressed as a start_date/end_date span of up to 31 days, and the no-dates default of the most recent report date (looking back a week). It does not name alternatives or say when to prefer a sibling tool (e.g., that report_id must first come from ams_market_report_search), which is left to the schema.

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.