Skip to main content
Glama

Itaú MCP

by io.github.mcp-dir

openfinance_update_transaction_category

Corrects the category of one or more transactions (PATCH /transactions/:id). Pass items as an array of { transaction_id, category_id } — transaction_id comes from openfinance_list_transactions, category_id from openfinance_list_categories. This overrides Pluggy's automatic categorization AND teaches Pluggy: recategorizing a transaction automatically creates a Category Rule for this client (case-insensitive exact match on the transaction's data), so FUTURE similar transactions are categorized the same way — use this to fix miscategorized transactions and improve categorization accuracy going forward. Batch shape: returns { updated, results: [{ transaction_id, category, categoryId }], errors: [{ id, status, message }] } — per-item errors do not fail the whole batch.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added
  2. Removed
  3. Added
  4. Removed
  5. Added
  6. Removed
  7. First observed

TDQS

A4.5/5.0
Behavior5/5

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

The description richly details behavior beyond annotations: it is a PATCH operation that overrides automatic categorization, creates a Category Rule affecting future transactions, and describes batch error handling with per-item errors not failing the whole batch. This adds significant context that annotations alone do not provide.

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?

The description is fairly long but every sentence adds value: it starts with the core purpose, then input details, side effects, and output shape. It is well-structured and not overly verbose, though it could be slightly more concise.

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?

The description covers the main aspects: how to call (input shape), what it does (override + teach), return shape, and error behavior. It lacks some operational details like rate limits or auth, but for a batch update tool with side effects, it is adequately complete.

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?

With 0% schema description coverage, the description compensates by explaining that transaction_id comes from list_transactions and category_id from list_categories, and that items is an array with required fields. This adds meaning beyond the raw schema, though it does not specify formats or constraints.

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?

The description explicitly states the tool 'corrects the category of one or more transactions' and identifies the HTTP method PATCH. It distinguishes from sibling tools like list_transactions and list_categories by specifying the exact IDs needed from them, making the purpose clear and unique.

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?

The description provides clear context for when to use the tool: 'fix miscategorized transactions and improve categorization accuracy'. It also explains the side effect of creating a Category Rule, which guides usage. However, it does not explicitly mention when not to use or list alternatives, though the context is sufficient.

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

All Itaú MCP toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation3/5

The Open Finance tools have clear list/get pairs for each resource (accounts, transactions, loans, investments, bills), but the marketplace tool is a monolith combining search, describe, invoke, install, subscribe, and prompt library actions, causing ambiguity about which action to use. Additionally, openfinance_list_transactions and openfinance_list_transactions_by_item overlap in purpose but are distinguished by scope.

Naming Consistency3/5

The openfinance_* group follows a consistent verb_noun pattern (list, get, update, force_sync, etc.), but the platform tools (authenticate, connect, marketplace, show_version, report_bug, toolkit_info) use mixed bare verbs and nouns, creating two distinct conventions. Names like openfinance_list_transactions_by_item are longer but still consistent within the group.

Tool Count4/5

25 tools is at the heavy end, but the Open Finance domain alone justifies 17 tools covering distinct resources and operations. The platform tools add 8 more, though the marketplace tool bundles many sub-actions into one, inflating the effective count. The number is borderline but not excessive given the breadth of banking functionality.

Completeness5/5

The Open Finance surface is comprehensive with list/get for every major resource, plus support for sync, status, search, categories, and category updates. The platform tools cover authentication, connection status, marketplace operations, bug reporting, version, and toolkit state. No obvious gaps or dead ends in the workflow.

Resources