List pending charge confirmations and their status. Shows cobros in pending_confirmation state that await client verification. Filter by client or confirmation status (pending, confirmed, disputed, auto_confirmed).
| Name | Required | Description | Default |
|---|---|---|---|
| apiKey | No | ||
| status | No | ||
| orgSlug | Yes | ||
| clientId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It discloses that it shows cobros in pending_confirmation state awaiting client verification, which is useful. However, there is an internal ambiguity: it says 'pending' but offers filters for confirmed/disputed/auto_confirmed, yet doesn't clarify default behavior or whether non-pending are included. Lacks detail on return format or pagination.
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?
Two compact sentences with the key information front-loaded: what it lists, the state, and the available filters. No wasted words.
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 filtered list tool, it covers the resource and filters, but lacks specification of default scope (pending only vs all statuses), pagination, output fields, or auth requirements. The absence of an output schema makes this more necessary, leaving the agent somewhat in the dark about the response.
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%, so the description must compensate. It explains 'status' with the allowed enum values and mentions 'client' as a filter (clientId). However, it does not explain apiKey or the required orgSlug, though these are likely self-evident authentication/tenant identifiers. Partial compensation.
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 ('List') and resource ('pending charge confirmations'), and clearly states it shows cobros in pending_confirmation state. It distinguishes from siblings like finance_list_cobros and disputes_list by focusing on confirmation statuses.
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 provides clear context for when to use this tool: to list charge confirmations and filter by status. It does not explicitly name alternatives or exclusions, but the context is unambiguous and implies this is the tool for confirmation status tracking.
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.
Multiple parallel booking creation flows (booking_create, scheduling_book, public_booking_create) and session state transition tools (booking_update_status, lifecycle_transition) create ambiguity. While descriptions are detailed, an agent could easily select the wrong tool for a given task, especially with 111 tools to choose from.
Most tools follow a consistent domain_action pattern (e.g., client_create, service_update, comms_list_campaigns). Minor deviations include Spanish/English mixing (cierre_*, report_deuda_real) and a few noun-only names like org_summary, but the overall structure is predictable.
With 111 tools, the server is massively over-scoped for an MCP surface. Even for a broad service business domain, this exceeds reasonable limits and will overwhelm agents, making tool selection slower and more error-prone.
The tool surface is extremely thorough, covering org setup, services, providers, booking (internal/public/spec), finance, payroll, closing, disputes, clinical notes, treatment plans, and reporting. Gaps are rare and often intentional (e.g., no deliver via MCP, read-only treatment plans), so agents can complete most workflows end-to-end.