Skip to main content
Glama

Classify a request

intake_classify
Idempotent

Classifies a customer request and opens the flow (REQUEST → CLASSIFIED). Never: Set an emergency tariff. Platform fee CHF 0.05 per accepted call: quote first, then send quote_id, mandate_token and idempotency_key.

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": {
      "mandate_token": "<mandate_token>",
      "text": "<text>"
    },
    "name": "intake_classify"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe customer's message as written, e.g. "Water under the sink, can someone come tomorrow?".
quote_idNoA valid quote for this capability (quote).
mandate_tokenYesThe mandate token from mandate.create.
idempotency_keyNoRequired on every mutate and money call; a retry with the same key returns the same result and is not charged again.
channel_message_idNoThe id of the message in its channel (WhatsApp, e-mail), so the same message is never taken twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / channel_message_id / description
      Added value: +"The id of the message in its channel (WhatsApp, e-mail), so the same message is never taken twice."
    • addedInput schema / properties / text / description
      Added value: +"The customer's message as written, e.g. \"Water under the sink, can someone come tomorrow?\"."
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, idempotent, non-destructive mutation, so the safety bar is lower and the description pays off elsewhere: it discloses the CHF 0.05 platform fee per accepted call and that the operation advances state to CLASSIFIED. It also implies the billing prerequisite (quote before call). What's missing is what happens to the request on failure or partial classification.

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?

Three dense sentences with no filler, and the action plus state transition are front-loaded ahead of constraints and pricing. The 'Never:' and 'quote first' fragments are telegraphic but each carries distinct information. Slightly compressed phrasing costs a little readability.

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?

Covers what the tool does, its state effect, its cost, the pre-call quote requirement, and an explicit exclusion, for a 5-parameter mutation with no output schema to document returns. An agent has enough to invoke it correctly and in the right order.

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 baseline would be 3; the description exceeds it by adding cross-parameter sequencing — quote_id, mandate_token and idempotency_key must be supplied together after a quote call — which the schema alone does not convey. It usefully resolves the ambiguity that idempotency_key is expected even though it is not in the required array.

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+resource ('Classifies a customer request') plus the resulting state transition (REQUEST → CLASSIFIED), which is more than a restatement of the name. It also carves out a scope exclusion ('Never: Set an emergency tariff'). It does not name a look-alike sibling such as intent_match or job_create, so an agent must still infer the boundary from the state-machine hint.

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 an explicit prerequisite ordering: 'quote first, then send quote_id, mandate_token and idempotency_key', which tells the agent the required call sequence before invoking. The 'Never:' clause adds a clear when-not case. No alternative sibling is named for the classify-vs-intent_match decision, so it stops short of full routing guidance.

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