Resolve um nome aproximado para o id/uuid real de conta, cartão ou categoria. Use ANTES de uma escrita para evitar ids inventados. Quando ambíguo, retorna as correspondências.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | ||
| name | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly=true, idempotent=true, and destructive=false. The description adds useful behavioral context: it performs approximate/fuzzy name resolution, returns multiple matches when ambiguous, and is meant as a safeguard before writes. This goes beyond what the annotations alone convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences, each earning its place: one for the core purpose, one for when to use it, and one for ambiguity behavior. It is front-loaded with the most important information and contains no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the tool's purpose, when to use it, and what happens on ambiguous input. Since there is no output schema, it also implies the return value is the real id/uuid. The only meaningful gap is explicit documentation of the `kind` parameter's allowed values and whether it is required, which is minor for a simple lookup tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It clearly explains the `name` parameter as the approximate name, but it does not explicitly describe the `kind` parameter's accepted values or optionality. The phrase 'conta, cartão ou categoria' hints at valid resource types but leaves the mapping to `kind` implicit.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('resolve') and states exactly what is resolved: approximate names to real ids/uuids for accounts, cards, or categories. It clearly differentiates itself from broader read-only tools by framing itself as a pre-write normalization step rather than a general list/search tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says to use this tool 'ANTES de uma escrita' (before a write) to avoid invented ids, which gives clear contextual usage. It does not name specific alternative tools or exclusion cases, but the guidance is strong enough for an agent to know when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct resource+action pairs, but the reporting/query side is crowded: get_balances, transactions_list_results, get_financial_summary, get_monthly_overview, and the category/tag reports overlap heavily. Long descriptions disambiguate bases and use cases, but an agent must read carefully to avoid picking the wrong report or list variant.
Organizze tools overwhelmingly follow a consistent organizze_<verb>_<noun> snake_case pattern with create_, list_, get_, update_, and delete_ prefixes. Deviations like transactions_list_results, the mass_* versus update_transactions_* bulk variants, and unprefixed platform tools keep it from being perfect.
68 tools is far beyond the practical agent surface and includes many near-variant list/report/mass tools plus six unrelated platform-level tools. Even though the finance domain is broad, this count creates an extreme mismatch for efficient tool selection.
The core finance lifecycle is well covered: accounts, cards, categories, budgets, transactions, invoices, transfers, and reports all have substantial CRUD or equivalent support. However, some referenced operations are missing entirely, such as delete_recurrence, clear_latest_imports, and remove_from_latest_imports, and transfers/recurrences lack full lifecycle coverage.