List appointments with optional filtering by status and date.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | End date in YYYY-MM-DD format | |
| from | No | Start date in YYYY-MM-DD format | |
| limit | No | Maximum number of results | |
| status | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations (readOnlyHint=true, destructiveHint=false, openWorldHint=true, idempotentHint=true) already convey that this is a safe, non-mutating read operation. The description adds the filtering capabilities by status and date, which is useful context. However, it does not disclose potential pagination behavior, default limits, or whether all appointments are returned when no filters are applied. As with the get_calls calibration, the annotations cover the safety profile, and the description provides some but not rich behavioral context.
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, front-loaded sentence: 'List appointments with optional filtering by status and date.' Every word is meaningful and there is no waste. It immediately states the action and resource, then adds the key optional modifiers, making it efficient and easy to parse.
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 tool has 4 optional parameters and no output schema, but the annotations are rich and the schema descriptions are fairly complete. The description covers the core function and filtering options, but it does not explain what happens with no filters (e.g., returns all appointments), address pagination, or mention the return format. For a list tool, this is adequate but not fully complete, especially without an output schema to fall back on.
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 75% (status lacks a textual description but has an enum). The description mentions 'status and date' as filtering options, which groups 'status', 'from', and 'to' semantically, but does not add detail beyond what the schema already provides for these parameters. The 'limit' parameter is not mentioned in the description, but the schema describes it as 'Maximum number of results'. Overall, the description adds minimal value beyond the schema, so a baseline of 3 is appropriate.
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 uses a specific verb ('List') and resource ('appointments'), clearly indicating a read operation that returns multiple records. It also mentions optional filtering by status and date, which distinguishes it from the sibling tool 'get_appointment' (singular) and implies a broader scope. The purpose is unambiguous and well-differentiated.
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?
No explicit guidance is given on when to use this tool versus alternatives. While the plural 'appointments' and 'List' imply it is for retrieving multiple records, there is no mention of when to choose this over 'get_appointment' or 'get_calendar_availability'. The description does not exclude any scenarios or state prerequisites, so the agent is left to infer usage from the name alone.
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.
Most tools are clearly distinct, but update_calendar overlaps with specialized tools like update_booking_settings, update_confirmation_settings, and the reminder management tools (add/delete/get reminders). This creates ambiguity about which tool to use for modifying specific settings such as buffers or reminders, though descriptions help clarify the intended scope.
All 28 tools follow a consistent verb_noun snake_case pattern (e.g., create_calendar, get_appointments, update_contact). The verbs are predictable (add, cancel, create, delete, get, reschedule, send, update), making the API easy to navigate.
With 28 tools, the set exceeds the 25+ threshold typically considered too many. While each tool serves a legitimate purpose, the high number is overwhelming and likely includes more granularity than necessary; some settings tools could be consolidated.
The tool surface covers the full lifecycle of calendars, appointments, and contacts, including availability, overrides, reminders, confirmation settings, and notifications. There are no obvious dead ends or missing operations; cancellation and rescheduling handle appointment changes, and send_invitation covers creation.
