Skip to main content
Glama

Kyrodata — Brazil Trade, Crop & Commodity Data

Top partner countries with growth

kyrodata_list_trade_partners
Read-onlyIdempotent

Ranks Brazil's partner countries for exports or imports, one row per country with value (USD FOB), volume (kg), price per kg and share of the window. from/to are YYYYMM and default to the last 12 published months; codes narrows to HS codes (4, 6 or 8 digits) so the ranking answers 'who buys THIS product'; withGrowth adds the last 12 months against the previous 12, which is the only way growth enters the answer. The country is the OUTPUT of this tool, so it takes no country filter — a question about one known country is a filter on kyrodata_compare_trade or kyrodata_list_trade_series instead. This ranks partners inside one window; comparing two windows is kyrodata_compare_trade. Credit class: comex (up to 2 comex tools per 60-second session = 1 credit).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoLast month of the window, as YYYYMM. Omit for the last published month.
flowYesDirection of the trade flow, from Brazil’s side: `export` leaves the country, `import` enters it.
fromNoFirst month of the window, as YYYYMM (200403 = March 2004). Omit for the last twelve published months.
codesNoProducts to filter by, as HS codes — 4 digits (heading), 6 (subheading) or 8 (Brazilian NCM), up to 10. Omit for every product. kyrodata_resolve_entity turns a product name into its code.
limitNoHow many partner countries to return, largest first by value.
withGrowthNoAlso return each partner’s growth: the twelve months ending at `to` against the twelve before them. It does NOT follow `from` — with a window of any other length, the ranking and the growth describe different periods.
response_formatNoHow 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
NameRequiredDescriptionDefault
dataYesRaw numbers behind the text.
memoYestrue = identical call in the last 10 min, served again: 0 credits.
rowsNoTable rows; detailed only, capped per tool.
errorNoFailure message when status = error.
linksYesscreen = product page with these numbers.
deniedNoWhen status = denied: reason, feature, upgradeUrl.
statusYesok = data; denied = plan; error = failure or timeout.
windowNoLike-for-like window: from, to (YYYY-MM), label, months, crossesSeason.
caveatsYesReading caveats.
creditsYescharged, balance (null = unlimited), resetAt, session {charged, endsAt} of the 60-s billing session.
sourcesYesPer source: label, nameable, asOf.
dataVersionYesIdentity of the data that answered.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / withGrowth / description
      Previous value: -"Also return each partner’s change against the same window a year earlier."New value: +"Also return each partner’s growth: the twelve months ending at `to` against the twelve before them. It does NOT follow `from` — with a window of any other length, the ranking and the growth describe different periods."
  2. Changed7 schema fields changed
    • addedInput schema / properties / codes / description
      Added value: +"Products to filter by, as HS codes — 4 digits (heading), 6 (subheading) or 8 (Brazilian NCM), up to 10. Omit for every product. kyrodata_resolve_entity turns a product name into its code."
    • addedInput schema / properties / flow / description
      Added value: +"Direction of the trade flow, from Brazil’s side: `export` leaves the country, `import` enters it."
    • addedInput schema / properties / from / description
      Added value: +"First month of the window, as YYYYMM (200403 = March 2004). Omit for the last twelve published months."
    • addedInput schema / properties / limit / description
      Added value: +"How many partner countries to return, largest first by value."
    • 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."
    • addedInput schema / properties / to / description
      Added value: +"Last month of the window, as YYYYMM. Omit for the last published month."
    • addedInput schema / properties / withGrowth / description
      Added value: +"Also return each partner’s change against the same window a year earlier."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real operational context beyond them: the credit class and rate limit (up to 2 comex tools per 60s = 1 credit), the quota cost of response_format=detailed, and the non-obvious withGrowth caveat that it ignores `from`.

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?

Dense but front-loaded: the ranking purpose and its output shape come first, then routing alternatives, then the credit note. Every clause carries information, though the single packed paragraph is heavier than strictly necessary.

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 7-parameter, one-required ranking tool with an output schema, the description covers purpose, window defaults, filtering semantics, growth behavior, sibling routing, and quota cost. Nothing an agent needs to call it correctly 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 goes beyond the schema by tying `codes` to the ranking intent ('who buys THIS product'), restating the YYYYMM default window, and warning that withGrowth is the only channel for growth. It adds intent-level meaning rather than raw syntax.

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 ('Ranks') and resource ('Brazil's partner countries for exports or imports') plus the row granularity (one row per country) and returned measures. It explicitly contrasts itself with kyrodata_compare_trade and kyrodata_list_trade_series, so an agent can distinguish it without opening a 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?

Explicitly states when to use it (ranking partners inside one window, 'who buys THIS product') and when not to (a question about one known country belongs on kyrodata_compare_trade or kyrodata_list_trade_series; comparing two windows is kyrodata_compare_trade). Alternatives and the selecting condition are named.

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.

Resources