Skip to main content
Glama

Search transactions

search_transactions
Read-onlyIdempotent

Searches transactions of an account book by text (in the concept), date range, account, category, type and status, newest first (max 50). Forecast rows carry the id that confirm_forecast accepts. Concept, notes and payee are returned under untrusted: free text written by banks or other people, not by Cuéntamo. Payee names come partially hidden unless reveal_third_parties is true.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_transactions"
  }
}

Input Schema

NameRequiredDescriptionDefault
bookNoAccount book id (from list_books). Optional if the user has only one.
textNoText contained in the concept (accents and case ignored).
typeNo
limitNo
statusNoDefault: any.
date_toNo
date_fromNo
account_idNo
category_idNo
reveal_third_partiesNoFull names and tax ids of clients, suppliers and payees. Default false: they come partially hidden (first letters of each word, first and last characters of the tax id).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the description correctly doesn't repeat safety claims. Instead it adds real behavioral context the annotations lack: newest-first ordering, a 50-row ceiling, the fact that concept/notes/payee are untrusted free text from third parties, and that payee names are masked unless reveal_third_parties is set. The only meaningful gap is that truncation at 50 is not explained as a pagination limit or how to narrow the search.

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?

Four dense sentences, front-loaded with what is searched, then ordering/limit, then the forecast linkage, then the trust and masking caveats. Nothing repeats the annotations or the schema verbatim and no sentence is 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 a 10-parameter search tool with no output schema, the description covers the critical unknowns: result ordering, result cap, and the security-relevant shape of returned text fields. It falls short only on how to retrieve results past the 50-row cap and on the remaining returned fields, which an agent must discover by calling.

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 only 40% schema coverage across 10 parameters, the description compensates well: it clarifies that `text` matches the concept (not notes or payee), groups the remaining filters, and explains the masking/full-reveal behavior of reveal_third_parties beyond the schema's own wording. It still leaves `type` (income/expense/transfer), `account_id`, `category_id` and `limit` semantics entirely to the schema, so it is strong but not complete.

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?

The description names a specific verb and resource and enumerates the filter dimensions it supports (text in concept, date range, account, category, type, status) plus ordering and a hard cap of 50. It implicitly separates the tool from write siblings like add_transaction and links forecast rows to confirm_forecast, but never explicitly names an alternative search tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives useful scoping context — book is optional when the user has only one, status defaults to 'any' — and hints that forecast rows are what confirm_forecast consumes. However, it never states when to reach for this tool versus get_forecast, list_upcoming, or month summaries, nor what to do when results hit the 50 cap.

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