Skip to main content
Glama

dietbox_anamnese_write_create

Create or update an anamnesis (health history questionnaire) in Dietbox. Actions:

  • create: cria nova anamnese. Obrigatório: patient_id. Opcional: descricao (título; default "Anamnese"), texto_livre (HTML; quando informado a anamnese é do tipo texto livre), data (ISO), overrides (campos da anamnese, ex.: {IsSmoking:true, HasDiabetes:true, Medicines:"Losartana", FoodAllergies:"camarão", Notes:"..."}; os nomes antigos fuma, diabetes, medicamentos, alergias, observacao também valem).

  • update: atualiza uma anamnese existente. Obrigatório: anamnesis_id E patient_id (o DietBox exige o paciente também na atualização). A anamnese é regravada inteira: envie todos os campos que devem continuar preenchidos (leia antes com dietbox_anamnese action=get). Retorna { id } da anamnese criada/atualizada.

[Flattened action: create]

Bulk support: accepts patient_ids, anamnesis_ids for batched execution.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "patient_id": "<patient_id>"
    },
    "name": "dietbox_anamnese_write_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNo
tipoNo
accountNo
descricaoNo
overridesNo
patient_idYes
patient_idsNo
texto_livreNo
anamnesis_idNo
anamnesis_idsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / required
      Added value: +[
      +  "patient_id"
      +]
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only cover the generic write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds genuinely useful behavior: the update path rewrites the whole anamnesis so all fields must be resent, the API additionally requires patient_id on update, and the response is { id }. It also explains the tipo/texto_livre interplay (supplying texto_livre switches the record to free-text). It does not cover error/failure behavior or whether partial writes are possible.

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

Conciseness3/5

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

The bulleted Actions structure is front-loaded and readable, and the overrides example earns its space. However the definition mixes English headers with Portuguese prose and spends a full bullet on the update branch that the flattened create action does not expose, which is wasted length for the caller of this tool.

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

Completeness3/5

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

It covers the create happy path, the whole-record overwrite hazard, and the return shape (no output schema exists, so that note is necessary). Against 10 parameters at 0% schema coverage and a nested overrides object, gaps remain: tipo's meaning, account, and how the batch arrays behave are never addressed, leaving an agent guessing on roughly a third of the surface.

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

Parameters3/5

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

Schema description coverage is 0% across 10 parameters, so the description must carry the load and it only partly does. It explains patient_id, descricao, texto_livre, data and overrides in depth (including concrete field keys and accepted legacy aliases like fuma/diabetes/medicamentos), but leaves tipo, account, anamnesis_id vs anamnesis_ids and patient_ids semantics unexplained, and never says how the bulk arrays interact with the singular required patient_id.

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

Purpose4/5

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

States a concrete verb and resource ("Create ... an anamnesis (health history questionnaire) in Dietbox") and enumerates the required and optional fields for the create branch. The opening "Create or update" is muddied by the presence of a sibling dietbox_anamnese_write_update and the trailing "[Flattened action: create]", so the agent must reconcile two framing signals before it is sure this tool only creates.

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

Usage Guidelines4/5

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

Gives clear per-action prerequisites: create needs only patient_id, update needs both anamnesis_id and patient_id, and it explicitly tells the agent to read the record first via dietbox_anamnese action=get before overwriting. Bulk support via patient_ids/anamnesis_ids is called out. No explicit when-not guidance, and the referenced read tool name does not match the sibling naming (dietbox_anamnese_get), which weakens the routing slightly.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.