Skip to main content
Glama

Prepare an inquiry (never sends)

prepare_inquiry

Prepare a request about one yacht for the person to review and send themselves on yachtfinder.co. This tool never sends anything: it saves a draft (the yacht, optional dates and up to 5 short questions) and returns one link. Give the person the link and tell them plainly that nothing has been sent: on that page they read and edit the draft, sign in, add their own details, and only their tap on Send sends it, under the usual inquiry limits. Take yacht from the id of a find_yachts, yachts_near or yacht_facts answer; a name is not searched. Questions are shown as plain text: links, markup and line breaks are removed. Do not put names, email addresses or phone numbers in them. The draft expires after 24 hours.

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": {
      "yacht": "<yacht>"
    },
    "name": "prepare_inquiry"
  }
}

Input Schema

NameRequiredDescriptionDefault
yachtYesThe yacht's id from another answer (its `id` field). Not a name and not a link.
date_toNoLast day of interest, YYYY-MM-DD, with date_from.
date_fromNoFirst day of interest, YYYY-MM-DD: today or later, at most 12 months ahead.
questionsNoUp to 5 questions for the listing broker, each at most 300 characters, in the person's words.

Output Schema

NameRequiredDescriptionDefault
urlYesThe page where the person reviews, edits and sends the draft.
sentYesAlways false: this tool never sends.
notesYes
yachtNo
sourceYes
summaryYes
data_as_ofYesWhen YachtFinder last rebuilt the catalog this answer was read from (ISO 8601).
expires_atYes
questions_keptNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations: it discloses that nothing is sent, that only the person's tap on Send sends it, that the draft expires after 24 hours, that questions are sanitized (links, markup and line breaks stripped), and that usual inquiry limits apply. The annotations only say this is a non-idempotent, non-destructive write with a closed world; the description supplies the real operational context. A slightly fuller account of the returned link or edit flow would push this to 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.

Conciseness4/5

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

Front-loaded with the single most important fact ('never sends'), and every sentence carries usable information. It runs a little long across six sentences, but there is essentially no filler.

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 4-parameter mutation tool with an output schema present, the description covers everything the agent needs: input provenance, the human-in-the-loop send flow, the sanitization of question text, sign-in requirements, expiry and limits. Nothing material is left to inference.

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 adds genuine meaning: it warns that `yacht` must be an id, not a name or link, and that questions must be the person's own words with no names, emails or phone numbers, and are rendered as plain text after stripping links and markup. Those are behavioral constraints on the parameter values that the schema does not express.

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 ('Prepare a request about one yacht') and immediately scopes the outcome ('never sends ... saves a draft ... returns one link'). It is clearly distinguished from the read-only siblings find_yachts, yachts_near and yacht_facts, which it names as the source of its input.

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?

Explicitly tells the agent where the `yacht` value comes from ('the `id` of a find_yachts, yachts_near or yacht_facts answer; a name is not searched') and what the agent must do with the result ('give the person the link and tell them plainly that nothing has been sent'). The not-to-do side is also covered via the PII prohibition on questions.

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