Skip to main content
Glama

Feegow Clinic

by io.github.mcp-dir
OverviewDiscussionsAdmin

feegow_appointment_write_cancel

Create, cancel, reschedule, or update status of appointments in Feegow. Actions:

  • create: new appointment. Requires local_id, paciente_id, profissional_id, especialidade_id, procedimento_id, data (DD-MM-YYYY), horario (HH:MM:SS 24h), valor (centavos), plano (0=no insurance, 1=insurance). Optional: convenio_id, convenio_plano_id, canal_id, tabela_id, notas, celular, telefone, email, retorno, sys_user.

  • cancel: requires agendamento_id, motivo_id. Optional: obs. (reversible status flip — not a hard delete).

  • reschedule: requires agendamento_id, motivo_id, data (DD-MM-YYYY), horario (HH:MM:SS). Optional: obs.

  • update_status: requires AgendamentoID, StatusID. Optional: Obs, HoraChegada (HH:MM for waiting status).

[Flattened action: cancel]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataYes
accountNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

D1.8/5.0
Behavior2/5

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

Annotations show readOnlyHint=false, destructiveHint=false, which are consistent with a cancel operation. The description adds that cancel is 'reversible status flip', which is helpful. However, the massive mismatch between described parameters (detailed lists) and actual schema (only data and account) undermines transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is excessively long (multiple action cases) for a tool that likely only cancels. Important info is buried, and irrelevant details for other actions are included. Not concise or front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Though the tool appears complex (multiple actions implied), the actual schema has only 2 params with no output schema. The description fails to explain the schema mismatch, leaving an agent confused about what parameters to use. Incomplete and misleading.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%: the description does not explain the actual parameters ('data' and 'account') at all. Instead, it lists many parameters for hypothetical actions that do not match the schema. No semantic value added for the real parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description lists multiple actions (create, cancel, reschedule, update status) but the tool name and sibling tools strongly indicate it is for cancel only. The flattened action '[cancel]' contradicts the body. Purpose is vague and not specific to the tool's role.

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

Usage Guidelines2/5

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

No explicit when-to-use guidance. The description suggests the tool can perform any action, but sibling tools for other actions exist, creating confusion about when to use this vs. others.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Feegow Clinic toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources