Use in trusted telephony flows when the caller number is already verified by the channel provider and you need a short-lived booking session without OTP.
| Name | Required | Description | Default |
|---|---|---|---|
| identifier | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden for disclosing behavior. It reveals the session is 'short-lived' and requires no OTP, but it omits side effects, prerequisites beyond number verification, what the identifier represents, and whether the tool creates a booking or just a session. This leaves substantial ambiguity about the tool's actual behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that front-loads the primary use case and includes no filler. Every word contributes to the intended scenario.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description specifies the trigger condition but fails to explain what the session does, how it fits into the booking flow, or what the identifier means. Given the lack of an output schema and the presence of many sibling booking tools, an agent would struggle to use this tool correctly without additional information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides only a name and length constraints for 'identifier', with zero description coverage. The tool description does not explain what the identifier is (e.g., caller phone number, session token), leaving the agent without any semantic guidance for the parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool's purpose: starting a trusted phone booking session without OTP when the caller number is already verified. It specifies the verb ('start'), the resource ('trusted phone session'), and the distinguishing condition (no OTP), which separates it from OTP-based verification siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit use context: 'Use in trusted telephony flows when the caller number is already verified...' This tells the agent when to apply the tool, though it does not explicitly state exclusions or name alternative tools. The context is clear enough for the intended scenario.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Some tools overlap in purpose, such as check_availability vs get_customer_availability and the various verification entry points. Descriptions clarify the context of each, but an agent could still misselect without careful reading.
All tools follow a consistent verb_noun pattern with snake_case, e.g., check_availability, create_booking_request, get_booking_status. This makes the naming predictable and easy to navigate.
With 20 tools, the server is on the heavier side but the scope is broad, covering booking, customer verification, payments, and provider matching. The count feels slightly high but each tool serves a distinct step in the workflow.
The tool surface covers the full booking lifecycle from availability and quote to payment and final creation. Notable gaps include lack of update or cancel booking operations, but the core flow is well covered.