Skip to main content
Glama

Resident: Larchmont Village Oral Surgery

Send an authorized LVOS staff follow-up request

send_appointment_request
DestructiveIdempotent

Sends an LVOS staff follow-up request that the user has explicitly authorized, using the confirmation token and idempotency key issued for those exact details. Saves an encrypted copy (deleted after 30 days) and emails practice staff, who contact the person. Repeating with the same idempotency key returns the original receipt. Does not book, reserve or confirm an appointment.

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": {
      "practice_id": "<practice_id>",
      "first_name": "<first_name>",
      "last_name": "<last_name>",
      "contact": "<contact>",
      "appointment_type": "<appointment_type>",
      "idempotency_key": "<idempotency_key>",
      "confirmation_token": "<confirmation_token>",
      "authorization_confirmed": "<authorization_confirmed>"
    },
    "name": "send_appointment_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
contactYesExactly one way for staff to reach the patient.
last_nameYesPatient last name, for example Lopez.
first_nameYesPatient first name, for example Maria.
practice_idYesAlways LVOS (Larchmont Village Oral Surgery).
idempotency_keyYesThe idempotency_key returned by prepare_appointment_request. Reuse it when retrying after an uncertain response.
appointment_typeYesconsult: the practice's 'Consult' type (about 30 minutes). surgery_consult: its 'Surgery Consult' type (about 60 minutes). Staff confirm the right type.
confirmation_tokenYesThe confirmation_token returned by prepare_appointment_request. Valid for 15 minutes and only for the unchanged details.
preferred_day_or_timeNoOptional scheduling preference, for example 'weekday mornings'. Not an available or reserved slot. No clinical details.
authorization_confirmedYestrue only when the user has explicitly authorized sending the exact prepared details after seeing the disclosure.

Output Schema

NameRequiredDescriptionDefault
codeNo
statusNo
messageNo
practice_idNo
submission_idNo
idempotency_keyNo
notification_statusNo
retry_after_secondsNo
confirms_appointmentNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / appointment_type / description
      Previous value: -"consult: the practice's 'Consult' type (about 30 minutes). surgery_consult: its 'Surgery Consult' type (about 60 minutes). If unsure, use consult; staff confirm the right type."New value: +"consult: the practice's 'Consult' type (about 30 minutes). surgery_consult: its 'Surgery Consult' type (about 60 minutes). Staff confirm the right type."
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, yet the description still earns credit by disclosing data retention (encrypted copy deleted after 30 days), the real-world side effect (emails practice staff who then contact the person), and retry semantics. It leaves unexplained what specifically makes the call destructive/irreversible — presumably the outbound email to real staff — which keeps it below a 5.

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

Conciseness5/5

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

Four short sentences, front-loaded with the verb and authorization constraint, followed by persistence, side effect, idempotency, and the negative scope. No filler and nothing repeated from the annotations.

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

Completeness4/5

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

For a high-stakes external-messaging mutation, the description covers authorization, token provenance, retention, real-world effect, retry behavior, and non-scope, and an output schema exists so return values needn't be described. The only residual gap is why the call is flagged destructive and whether the sent email can be recalled.

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 100%, so the baseline is 3. The description echoes the roles of confirmation_token and idempotency_key but adds no format, scope, or edge-case detail beyond what the schema already documents for all nine parameters.

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

Purpose5/5

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

States a specific verb and resource ("Sends an LVOS staff follow-up request") plus its authorization precondition, and explicitly negates the adjacent concept ("Does not book, reserve or confirm an appointment"). An agent can distinguish this from prepare_appointment_request and from any booking-style tool without opening a schema.

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 call conditions: the user must have explicitly authorized the exact prepared details, the confirmation token and idempotency key must come from that preparation, and repeats with the same key return the original receipt. It also fences off the tempting-but-wrong use (booking). It stops short of naming the alternative or the step-by-step precondition tool.

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.

Resources