Lista as contas bancárias ativas da agência no iClips (id, nome, isDefault, banco, agência e número da conta). Use o id retornado como account_id ao filtrar iclips_financial_entries. Não tem filtro nem paginação: devolve sempre todas as contas ativas.
| Name | Required | Description | Default |
|---|---|---|---|
| account | 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?
Annotations already mark it read-only, idempotent and non-destructive. The description adds real behavioral facts: there is no filter or pagination and it always returns all active accounts. This is consistent with the annotations.
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 with no filler: purpose and return fields, downstream usage, and constraints are each given a sentence. The most important scoping information appears first.
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?
For a simple read-only list, the description covers the returned fields and calling constraints well. However, the presence of an optional 'account' parameter that the description says is not a filter creates a completeness gap; an agent cannot be fully sure how to handle it.
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% and the only parameter 'account' is undocumented. The description's 'Não tem filtro nem paginação' implies the parameter does not act as a filter, but it never states whether the parameter is ignored, deprecated or used for something else.
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 names a specific operation ('Lista') on a specific resource ('contas bancárias ativas da agência no iClips') and enumerates returned fields. It is clear and precise, but it does not explicitly differentiate from the similar-sounding sibling iclips_list_accounts.
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 gives clear downstream guidance ('Use o id retornado como account_id ao filtrar iclips_financial_entries') and states the tool's no-filter/no-pagination behavior. It does not mention when to prefer this over iclips_list_accounts, so it stops short of full alternatives 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.
Many tools are near-duplicates, such as iclips_financial_entries_get/list, iclips_pieces_get/list, iclips_pieces_write_create/update/checklist, and iclips_workflow_templates_get/list, all sharing essentially the same description. authenticate and connect also overlap on session/connection status, so an agent must rely on brittle naming conventions rather than clear semantic boundaries.
The iClips tools mostly follow iclips_<resource>_<action>, but the server mixes noun-only names like iclips_financial_accounts and marketplace, camelCase platform names like toolkit_info and show_version, and artificial get/list flattened duplicates. The pattern is only predictable within a subset of the tool list, not across the entire server.
At 30 tools, the set is over-inflated for its actual scope: most are flattened get/list or write-action variants of roughly a dozen underlying iClips operations, plus six unrelated platform utilities. The domain could be cleanly served in about half this many tools without losing functionality.
Jobs and pieces have reasonable CRUD coverage, but there is no client/group or destination master lookup even though clientId is required to create a job and destination_id filters financial entries. Job pieces and tasks also lack delete operations, and financial categories are not enumerable, leaving noticeable dead ends for common workflows.