Skip to main content
Glama

Send an inquiry to the operator

send_inquiry

Send one inquiry from a traveler to the operator of a passport, by email through Ospitario (no booking, no payment, no commission). Two steps, and only with the traveler's consent: first call without code; Ospitario mails a six-digit code and a confirmation link to guest_email. Ask the traveler for the code, then call again with challengeId and code; if the traveler confirmed with the link instead, the inquiry is already sent and that call answers refused with reason used. The operator replies to the traveler's address directly. For an unclaimed passport (L0) this is the only way to write. Limits: 3 per traveler email and day, 10 per operator and day, identical messages once. When sent, the answer carries a reference that the operator's mail names too; give it to the traveler.

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": {
      "slug": "<slug>",
      "guests": "<guests>",
      "message": "<message>",
      "guest_email": "<guest_email>"
    },
    "name": "send_inquiry"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoCheckout date YYYY-MM-DD; requires from
codeNoThe six-digit code the traveler received by email, for step 2
fromNoCheck-in date YYYY-MM-DD; requires to
langNoLanguage of labels in the result; defaults to en
slugYesPassport slug from a search or lookup result
guestsYesNumber of guests
messageYesThe traveler's message to the operator, in the traveler's words
challengeIdNoFrom step 1; send it with code in step 2
guest_emailYesThe traveler's email address; the operator replies there

Output Schema

NameRequiredDescriptionDefault
reasonNoWhy nothing was sent: limits (3 per traveler and day, 10 per operator and day), the operator opted out, a repeated identical message, a wrong or expired code, used: already sent through the mail's confirmation link, delivery_failed: the mail server refused the mail (step 1: no code went out; step 2: the inquiry is recorded under reference but did not go out, the traveler may send it again), rate_limited: too many calls, try again in a minute
statusYescode_sent: the code was handed to the mail server for guest_email; ask the traveler for it, then call again with challengeId and code (the traveler may confirm with the mail's link instead). sent: the inquiry was handed to the mail server for the operator, Reply-To the traveler; it is not a sign the operator read or answered it, and answers go to guest_email, not to Ospitario. Calling step 2 again with the same challengeId and code returns the same reference. refused: see reason
referenceNoWith sent, or refused for delivery_failed: the inquiry's reference, also named in the operator's mail; quote it to the traveler and in any follow-up. Opaque, carries no personal data.
challengeIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare it is a non-destructive, non-idempotent, open-world write; the description adds substantially more: per-email and per-operator daily rate limits (3/10), duplicate suppression for identical messages, the out-of-band six-digit code challenge, the 'refused with reason used' outcome when the link was clicked, and the fact that the operator replies directly to the guest's address. It stops just short of describing failure modes for exceeded limits or expired codes.

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

Conciseness4/5

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

Front-loaded with purpose, then the two-step flow, then limits, then the returned reference — a sensible order with no filler. It is a single dense paragraph, though, and the limits/reference clauses would scan faster as separate sentences or lines.

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

Completeness5/5

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

For a 9-parameter, stateful, rate-limited mutation with an output schema, this covers everything an agent must know: consent, ordering, code delivery, the alternate link-confirmation path, quotas, and what to do with the returned reference. Return-value details are properly left to the output schema.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description still earns credit by explaining the temporal relationship between challengeId and code (step 1 output feeds step 2) and by naming guest_email as the destination of both the code and the operator's reply. It adds protocol-level meaning the per-field schema text cannot convey.

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?

Opens with a specific verb+resource+channel ('Send one inquiry from a traveler to the operator... by email through Ospitario') and immediately scopes it with 'no booking, no payment, no commission'. That distinguishes it plainly from the read-only siblings (get_passport, search_properties, lookup_*), so an agent can route correctly without opening any schema.

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

Usage Guidelines5/5

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

Gives an explicit two-step protocol (call without code, then with challengeId and code), a hard prerequisite ('only with the traveler's consent'), and a decisive condition for choosing this tool over anything else: 'For an unclaimed passport (L0) this is the only way to write.' It also tells the agent what to do if the traveler used the email link instead — no second call needed.

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