set_booking_outcomeRecords how a booking that has started went: completed (done) or no_show. Emails nobody; it can be changed between the two.
| Name | Required | Description | Default |
|---|---|---|---|
| site | Yes | ||
| item_id | Yes | ||
| outcome | Yes | ||
| plugin_id | No | Default: booking page |
| Name | Required | Description | Default |
|---|---|---|---|
| item_id | No |
Changes observed during successful MCP inspections.
Input schema / properties / item_id / descriptionRemoved value: -"From get_lists"Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "item_id": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Input schema / properties / plugin_id / descriptionPrevious value: -"Default: the booking page"New value: +"Default: booking page"Input schema / properties / site / descriptionRemoved value: -"Site name"Input schema / properties / plugin_id / descriptionPrevious value: -"Default: the site's booking page"New value: +"Default: the booking page"Input schema / properties / site / descriptionPrevious value: -"Site name, e.g. brave-otter-4821"New value: +"Site name"Output schema / (root)Previous value: -{
- "additionalProperties": {},
- "properties": {
- "agent_message": {
- "type": "string"
- },
- "confirm_token": {
- "type": "string"
- },
- "error": {
- "description": "On failure (isError): {code, message}"
- }
- },
- "type": "object"
-}New value: +nullInput schema / properties / item_id / descriptionPrevious value: -"From list_plugin_data"New value: +"From get_lists"Input schema / properties / plugin_id / descriptionPrevious value: -"From list_plugins"New value: +"Default: the site's booking page"Input schema / requiredPrevious value: -[
- "site",
- "plugin_id",
- "item_id",
- "outcome"
-]New value: +[
+ "site",
+ "item_id",
+ "outcome"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly=false, destructive=true, idempotent=true, closed-world, and the description adds genuinely new context: no notification emails are sent, and the value is switchable between the two states. That side-effect and reversibility disclosure is exactly what an agent needs before mutating a booking.
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?
One compact sentence with a colon-separated enumeration; the operation and its two outcomes are front-loaded and every clause carries information. No filler.
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 explained, and annotations plus the 'emails nobody / changeable' note cover the safety profile. Still missing is any explanation of the required site/item_id identifiers and what precisely counts as 'started', which is where an agent is most likely to call this wrongly.
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 coverage is only 25% (only plugin_id is documented as defaulting to the booking page). The description explains the outcome enum semantics ('completed (done) or no_show'), but says nothing about what 'site' and 'item_id' identify or their accepted formats, leaving the two most important required parameters undocumented in both schema and description.
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 ('Records how a booking ... went') plus the two allowed end states, so it is clearly distinct from approve_booking/cancel_booking/edit_booking in intent. It does not explicitly name those siblings, but the scope is unambiguous.
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?
'a booking that has started' sets a usable precondition that implicitly excludes future/pending bookings. However, it never says what to use instead for pending bookings (approve_booking, edit_booking, cancel_booking) or what happens if the booking hasn't started yet.
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.