Query the current state of any in-flight async operation by operation_id.
WHEN TO USE: Use to poll the state of a pending_async operation when no webhook callback has arrived or to check progress. WHEN NOT TO USE: Do not poll more frequently than once per 10 seconds — use webhook delivery for real-time updates instead. COST: free - no key required LATENCY: ~50ms
| Name | Required | Description | Default |
|---|---|---|---|
| operation_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, covering the safety profile. Description adds cost and latency details (~50ms, free/no key) and clarifies the polling context. No contradiction; additional info is useful but not extensive.
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 front-loaded with the core purpose, followed by clear WHEN TO USE/WHEN NOT TO USE sections, then cost/latency. No waste; every line earns its place and the structure is scannable.
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?
For a simple polling tool, it covers usage context, frequency limits, cost, latency, and safety via annotations. It does not describe return format or error handling, but given no output schema and the tool's simplicity, this is mostly complete. The lack of a return shape might matter, but the description still provides enough to call it correctly.
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?
Schema description coverage is 0%, so description must compensate. It mentions operation_id and that it identifies an in-flight async operation, but does not explain where it comes from, its format, or any constraints. For a single simple parameter, this is adequate but not thorough.
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?
States a specific verb ('Query') and resource ('current state of any in-flight async operation') with a clear parameter (operation_id). It implies it is for checking status, but does not explicitly differentiate from the sibling get_outcome, which may also query results. However, the focus on 'in-flight' and polling is distinct enough.
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?
Clearly specifies when to use (poll pending_async when no webhook) and when not to use (not more than once per 10s, use webhooks for real-time). Explicitly mentions the alternative (webhook delivery), leaving no ambiguity for the agent.
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.
Each tool maps to a distinct stage or concern: link preflight vs import, business discovery vs verification, scheduling, async status/outcome, cost preview, and health. The closest pair (check_booking_link and import_booking_url) is explicitly differentiated as a free guard vs actual registration.
Nearly all tools follow a consistent verb_noun snake_case pattern such as find_business, verify_business, schedule_appointment, and get_status. The only real deviation is self_test, which is a standard health-check name but not verb_noun.
Nine tools is well-scoped for an appointment-booking service that also needs async operation tracking, cost estimation, and health checks. Each tool has a clear role and none feel redundant or tacked on.
The toolset covers the main lifecycle: find or import an SMB, verify it, schedule/cancel/reschedule, poll status, retrieve outcomes, and preview costs. Minor gaps exist—send_message and capture_lead are referenced as downstream operations but not exposed, and there is no direct tool for listing supported platforms.