APAGA (exclui em definitivo) uma conta a pagar (ExcluirContaPagar). Informe codigo_lancamento_omie (id Omie) OU codigo_lancamento_integracao. Ação IRREVERSÍVEL — confirme com o usuário antes de chamar. Consulte antes com omie_get_payable pra ter certeza do lançamento.
| Name | Required | Description | Default |
|---|---|---|---|
| account | No | ||
| codigo_lancamento_omie | No | ||
| codigo_lancamento_integracao | No |
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?
The description states the action is irreversible, implying destructiveness, but annotations set destructiveHint to false. This contradiction misleads an AI agent about the tool's safety profile.
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 sentences, no wasted words. Purpose stated first, then critical usage notes. Every sentence adds necessary information.
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?
Provides essential steps (confirm, consult) but lacks details on return values, error cases, or what happens after deletion. However, for a deletion tool with no output schema, this is largely adequate.
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 coverage is 0%, but description adds meaning for codigo_lancamento_omie and codigo_lancamento_integracao by explaining mutual exclusivity. However, the 'account' parameter is not mentioned, leaving it undocumented.
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 clearly states it deletes (excludes) a payable account using either Omie ID or integration code. It distinguishes from siblings like omie_get_payable and omie_create_payable.
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?
Explicitly instructs to confirm with user before calling since action is irreversible, and advises consulting omie_get_payable first to verify the payable. Provides clear when-to-use and when-not-to-use guidance.
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.
The core Omie operations are distinct by resource and action, and the descriptions actively call out edge cases like omie_lancar vs omie_create_payable/receivable and transfer vs manual entries. A few pairs (list_payables/list_receivables/list_financial_movements/list_checking_account_entries) still overlap enough that an agent could pick the wrong one on first attempt.
The dominant pattern is clear and consistent: omie_verb_noun with create, get, list, update, delete, settle, cancel, and reconcile. The main deviations are the Portuguese helper omie_lancar and the unprefixed platform-level tools like authenticate, connect, marketplace, and toolkit_info, which break the otherwise regular naming scheme.
With 50 tools, this server is far beyond the 3-15 well-scoped range and sits at the extreme end of the rubric. Most of the tools are individually purposeful, but exposing checkings, payables, receivables, reconciliation, attachments, invoicing, batch upserts, and an entire marketplace platform in one server heavily taxes an agent's tool-selection space.
The core financial lifecycle is well covered: create, read, update, delete, settle, cancel, reconcile, unreconcile, transfer, attachment upload, and batch upsert. Minor gaps exist—invoices are list-only, customers have no delete operation, and there is no dedicated get-by-id for checking accounts—but these are workable for the main reconciliation workflows.