Mark times open for the shop's voice agent to book callers into (owner or office). The agent books them only when phone.setVoiceAi has book_open_slots true, which is off by default. Each slot is at most 12 hours and in the future. A booked slot becomes a request with that time for the office.
| Name | Required | Description | Default |
|---|---|---|---|
| slots | Yes | ||
| shop_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / properties / slots / items / properties / kindAdded value: +{
+ "description": "emergency: held for emergency calls only, booked by the voice agent only when the shop turned on emergency handling (phone.setEmergency). Default routine.",
+ "enum": [
+ "routine",
+ "emergency"
+ ],
+ "type": "string"
+}Output schema / anyOfPrevious value: -[
- {
- "properties": {
- "data": {
- "items": {
- "properties": {
- "booked": {
- "type": "boolean"
- },
- "ends_at": {
- "format": "date-time",
- "type": "string"
- },
- "request_id": {
- "format": "uuid",
- "type": [
- "string",
- "null"
- ]
- },
- "slot_id": {
- "format": "uuid",
- "type": "string"
- },
- "starts_at": {
- "format": "date-time",
- "type": "string"
- }
- },
- "required": [
- "slot_id",
- "starts_at",
- "ends_at",
- "booked"
- ],
- "type": "object"
- },
- "type": "array"
- }
- },
- "required": [
- "data"
- ],
- "type": "object"
- },
- {
- "properties": {
- "approval_id": {
- "format": "uuid",
- "type": "string"
- },
- "approval_required": {
- "enum": [
- true
- ],
- "type": "boolean"
- },
- "expires_at": {
- "format": "date-time",
- "type": "string"
- },
- "message": {
- "type": "string"
- },
- "status": {
- "enum": [
- "pending"
- ],
- "type": "string"
- }
- },
- "required": [
- "approval_required",
- "approval_id",
- "status",
- "expires_at",
- "message"
- ],
- "type": "object"
- }
-]New value: +[
+ {
+ "properties": {
+ "data": {
+ "items": {
+ "properties": {
+ "booked": {
+ "type": "boolean"
+ },
+ "ends_at": {
+ "format": "date-time",
+ "type": "string"
+ },
+ "kind": {
+ "enum": [
+ "routine",
+ "emergency"
+ ],
+ "type": "string"
+ },
+ "request_id": {
+ "format": "uuid",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "slot_id": {
+ "format": "uuid",
+ "type": "string"
+ },
+ "starts_at": {
+ "format": "date-time",
+ "type": "string"
+ }
+ },
+ "required": [
+ "slot_id",
+ "starts_at",
+ "ends_at",
+ "booked",
+ "kind"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "data"
+ ],
+ "type": "object"
+ },
+ {
+ "properties": {
+ "approval_id": {
+ "format": "uuid",
+ "type": "string"
+ },
+ "approval_required": {
+ "enum": [
+ true
+ ],
+ "type": "boolean"
+ },
+ "expires_at": {
+ "format": "date-time",
+ "type": "string"
+ },
+ "message": {
+ "type": "string"
+ },
+ "status": {
+ "enum": [
+ "pending"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "approval_required",
+ "approval_id",
+ "status",
+ "expires_at",
+ "message"
+ ],
+ "type": "object"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden and does add real behavioral context: the 12-hour maximum duration, the future-only constraint, and the downstream effect that a booked slot becomes a request for the office. It does not state whether creation requires owner permissions, whether duplicates are rejected or merged, or how to undo (the removeOpenSlot sibling is never mentioned).
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?
Four sentences, front-loaded with the purpose sentence, then gating, constraints, and outcome. No filler; the only mildly expendable detail is the redundant 'owner or office' aside.
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?
An output schema exists, so return values need not be described, and for a two-parameter mutation the description covers purpose, precondition, validation limits, and downstream effect. Missing pieces — permission requirements, duplicate/overlap handling, and removal path — keep it short of full completeness for an unannotated write tool.
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% for the top-level parameters, so the description must compensate; it does add meaningful constraints on the time values (at most 12 hours, must be in the future) and explains what a slot semantically represents. It says nothing about shop_id or the array bounds (1–50 items), and the kind enum is documented only inside the schema.
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 and resource: mark times open for the shop's voice agent to book callers into, and clarifies the office/owner scope. The action is unmistakably an additive slot creation, distinguishable from schedule_openSlots (read) and schedule_removeOpenSlot (removal), though those siblings are never named.
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?
Gives an important precondition — slots are only actually booked when phone.setVoiceAi has book_open_slots true, which is off by default — so an agent knows adding slots may be a no-op. It stops there: no guidance on when to use this versus schedule_setShopHours, schedule_setRules, or schedule_findTime, and no statement of what happens if a slot overlaps an existing one.
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.