Skip to main content
Glama

book appointment by phone

book_appointment_by_phone
Read-only

Have an AI place a real phone call to a restaurant, salon, clinic or hotel to book, reschedule or ask a question, using LifeClaw on Finch. Returns the agent's official description, price, free runs, a run link and a ready-to-send request.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "book_appointment_by_phone"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskNoOptional short description of what the user wants. Do not include private documents or secrets.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

The description adds context beyond the annotations: it discloses the external actor ('LifeClaw on Finch'), the cost signals ('price, free runs'), and the returned payload ('agent's official description… run link… ready-to-send request'). This is coherent with the openWorldHint=true/readOnlyHint=true pairing since the tool prepares a request rather than mutating directly. Still, the leading 'have an AI place a real phone call to book' framing is ambiguous about whether the MCP call itself places the call or only produces a request, which could mislead an agent.

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?

Two efficient sentences that front-load the core purpose before listing the returned payload. Nothing is redundant, though the second sentence packs multiple return items densely.

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

Completeness3/5

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

There is no output schema, and the description does compensate by enumerating return values (agent description, price, free runs, run link, request). However, the key ambiguity of whether the call is executed or merely prepared is left unresolved, which is important for a task that implies real-world action.

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 lone 'task' parameter is fully documented with guidance to omit secrets. The description adds no extra semantics for 'task,' so the baseline 3 is appropriate.

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 concrete verb and resource with domain scope: 'place a real phone call to a restaurant, salon, clinic or hotel to book, reschedule or ask a question.' This is distinguishable from sibling finch tools like search_finch_agents or get_finch_agent, which surface agents rather than initiate a booking flow.

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

Usage Guidelines3/5

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

The description names the three use cases (book, reschedule, ask a question) so the when-to-use is implied clearly. However, it does not name alternatives (e.g., how_to_call_finch_agents, get_finch_agent) or say when NOT to use it, so an agent must infer selection among siblings.

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.