PATCH /notifications — Update your notification preferences
Update any subset of your notification preferences. Send only the categories/channels you want to change — the rest stay as-is. Email is rejected for reaction / myReaction (not supported).
⚠️ WRITE operation: this mutates your DC account data.
| Name | Required | Description | Default |
|---|---|---|---|
| categories | Yes | Per-category push/email toggles. Pass only the categories + channels you want to change. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden. It explicitly states it is a WRITE operation that mutates data and mentions a specific rejection case. However, it does not cover idempotency, authorization requirements, or rate limits, which are typical for mutation tools.
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 extremely concise with three sentences. It front-loads the HTTP method and purpose, includes a usage guideline, and a warning. No wasted words.
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 tool with one parameter and no output schema, the description covers the operation, partial update behavior, and a specific error condition. It does not mention response format or error codes, but it is largely sufficient for an agent to understand how to use 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 coverage is 100%, baseline 3. The description adds value by reinforcing the partial update behavior (PATCH semantics) and the constraint on email for reaction/myReaction, which is not in the schema. It enhances understanding beyond the schema 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?
The description clearly states the verb (Update) and resource (notification preferences). It includes the HTTP method PATCH, which distinguishes it from siblings like 'notifications' (likely a GET). However, it does not explicitly differentiate from other update tools.
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 explains when to use it: to update a subset of preferences, and provides a specific constraint: email is not supported for reaction/myReaction. It lacks explicit alternatives (e.g., for reading use 'notifications'), but the context is clear enough.
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.
Despite the large number of tools, each has a detailed description that clearly distinguishes its purpose. Minor potential overlaps (e.g., search vs. resource-specific search, own vs. other's agenda) are well documented, so an agent can differentiate them.
Tool names follow a consistent verb_noun or resource_subresource_action pattern in snake_case. A few tools are just nouns (e.g., 'alerts', 'announcements'), but these are top-level listing endpoints; overall the naming is predictable.
85 tools is very high for a single server, making it difficult for an agent to efficiently explore and select the right tool. While each tool seems justified for the broad domain, the count feels overwhelming and could be streamlined.
The tool surface covers most major areas (events, trips, chapters, rooms, search, profile, etc.) with CRUD or lifecycle operations. However, the lack of a 'send message' tool for rooms is a notable gap, and some resources (e.g., events) are read-only on creation/update, limiting agent workflows.
