Kyrodata — Commodity Price Forecasts & Trade Intelligence

Supply and demand balance sheet

kyrodata_get_supply_demand_balance

Read-onlyIdempotent

Published supply and demand balance (physical, in tonnes) for one agricultural hub, season by season: production, imports, exports, consumption, initial and final stock, whether the season is still an estimate, and how many months a partial season measures. hub accepts only the hubs that have a published balance sheet, which is fewer than the hubs the forecast tools cover; closedOnly drops the current season, which is a projection and still moves. The source is a Brazilian government body and is named in the result. This is the physical BALANCE of a season. The price verdict for the same hub is kyrodata_get_hub_summary, and the weather risk behind production is kyrodata_get_climate_reading. Credit class: level (any level tool in a 60-second session = 2 credits; a session is capped at 3).

Input Schema

TableJSON Schema

Name	Required	Description
`hub`	Yes	Which commodity hub to read. Only hubs with a published balance sheet appear here.
`closedOnly`	No	Restrict to seasons already closed. The current season is a projection and still moves.
`response_format`	No	How much of the answer to return. `concise` (the default) carries the headline figures; `detailed` adds the row-level series behind them and counts against the export quota.

Output Schema

TableJSON Schema

Name	Required	Description
`data`	Yes	Raw numbers behind the text.
`memo`	Yes	true = identical call in the last 10 min, served again: 0 credits.
`rows`	No	Table rows; detailed only, capped per tool.
`error`	No	Failure message when status = error.
`links`	Yes	screen = product page with these numbers.
`denied`	No	When status = denied: reason, feature, upgradeUrl.
`status`	Yes	ok = data; denied = plan; error = failure or timeout.
`window`	No	Like-for-like window: from, to (YYYY-MM), label, months, crossesSeason.
`caveats`	Yes	Reading caveats.
`credits`	Yes	charged, balance (null = unlimited), resetAt, session {charged, endsAt} of the 60-s billing session.
`sources`	Yes	Per source: label, nameable, asOf.
`dataVersion`	Yes	Identity of the data that answered.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 29, 2026

changedInput schema / properties / hub / enum

Previous value: -[
-  "soybean",
-  "corn",
-  "wheat",
-  "cotton",
-  "beef",
-  "chicken",
-  "pork",
-  "coffee",
-  "sugar"
-]New value: +[
+  "soybean",
+  "corn",
+  "wheat",
+  "rice",
+  "cotton",
+  "beef",
+  "chicken",
+  "pork",
+  "coffee",
+  "sugar"
+]

Changed3 schema fields changedSep 7, 2026

addedInput schema / properties / closedOnly / description

Added value: +"Restrict to seasons already closed. The current season is a projection and still moves."

addedInput schema / properties / hub / description

Added value: +"Which commodity hub to read. Only hubs with a published balance sheet appear here."

addedInput schema / properties / response_format / description

Added value: +"How much of the answer to return. `concise` (the default) carries the headline figures; `detailed` adds the row-level series behind them and counts against the export quota."

First observedSep 6, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description layers on real added context: the Brazilian government source is named in the result, the current season is a live projection, and the credit cost model (level class, 2 credits, 3-credit session cap). This is well beyond what the annotations declare.

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, then routing, then a caveat and credit note. Every sentence carries information, though the credit-class sentence is longer than strictly needed and marginally dilutes the flow.

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?

With a full output schema and rich annotations, the description need not explain return values; it instead supplies the cross-tool routing, hub-coverage caveat, projection caveat, source attribution, and cost model that an agent needs to invoke it 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, but the description adds meaning beyond the schema: it clarifies that `hub` only accepts hubs with a published balance sheet—fewer than the forecast tools cover—and explains why `closedOnly` exists (the current season is a projection and still moves). These rationales exceed the schema's own text.

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 ('published supply and demand balance, physical, in tonnes, for one agricultural hub, season by season') and enumerates the contents (production, imports, exports, consumption, stocks, estimate flag). It explicitly distinguishes itself from siblings by naming kyrodata_get_hub_summary for price and kyrodata_get_climate_reading for weather risk.

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 explicit routing: price verdict goes to kyrodata_get_hub_summary, weather risk to kyrodata_get_climate_reading. It also states when `closedOnly` is appropriate (dropping the current projection that still moves) and warns that `hub` covers fewer hubs than the forecast tools.

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

All Kyrodata — Commodity Price Forecasts & Trade Intelligence 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.