Skip to main content
Glama

Request a callback

request_callback

Ask an entry to call the user back, about what they want to talk about, at times that suit them. Only for entries whose actions (get_entry_sections) list request_callback. Ask the user for their name, email address and phone number. Nothing is sent by this call: the user sends it on Daawid's page, with a code Daawid emails them. Give the user the link from the answer.

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": {
      "entry": "<entry>",
      "requester": "<requester>",
      "topic": "<topic>"
    },
    "name": "request_callback"
  }
}

Input Schema

NameRequiredDescriptionDefault
entryYesWhich entry: its ID or slug, from search or get_entry.
topicYesWhat the user wants to talk about, in their words and language. Don't add what they didn't say.
answersNoAnswers to the action's own questions (get_entry_sections), by their keys.
actionIdNoWhich of its actions of this kind (get_entry_sections), when it has several.
requesterYes
offeringIdNoWhich of the entry's offerings (get_entry_sections) it is about, if one.
idempotencyKeyNoYour own key for this request: the same key and details within 24 hours give the same request.
preferredTimesNoWhen a call suits the user: up to 3 windows. Leave out when any time does.

Output Schema

NameRequiredDescriptionDefault
urlNo
kindYes
entryYes
runIdNo
statusYes
summaryYes
expiresAtNo
confirmUrlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare a non-read-only, open-world, non-destructive mutation, and the description adds the critical thing annotations cannot: this call sends nothing, the user completes it on Daawid's page with an emailed code, and the agent must hand over the link from the response. That is a genuinely unusual two-phase flow disclosed clearly. It omits failure modes and what happens if the user never completes the flow.

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 action and its gate, then the required user data, then the completion flow — a sensible order with no filler. The opening clause ('about what they want to talk about, at times that suit them') is slightly loose prose that the schema fields state more precisely.

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 an 8-parameter, nested-object tool with an output schema, the description covers the essentials an agent needs: eligibility, the three facts to collect, and the instruction to pass the link to the user. Since return values are documented by the output schema, the remaining gap is minor — mostly the absence of guidance on the non-eligible path.

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 88%, so the schema already explains entry, topic, answers, actionId, offeringId, idempotencyKey and the preferredTimes windows in detail. The description only echoes the requester fields ('Ask the user for their name, email address and phone number'), which the schema already covers with 'Ask them; don't guess', so it adds little meaning beyond the structured data. Baseline 3 applies.

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: 'Ask an entry to call the user back', plus scope ('at times that suit them'). The eligibility clause referencing entry actions implicitly separates it from other request-type tools, but it never names the nearby alternatives (request_appointment, request_quote, get_request_status) so the routing is inferred rather than stated.

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 precondition ('Only for entries whose actions (get_entry_sections) list request_callback') and a concrete pre-call checklist ('Ask the user for their name, email address and phone number'). It does not state what to do when the action is absent — presumably fall back to another request tool — so the exclusion path is left implicit.

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