get_notifications

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description is the sole source. It describes the return fields (list, total, unread) and filter options, but does not disclose whether it's read-only, auth requirements, or rate limits. It adds useful context but could be more transparent.

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 two sentences, front-loading the purpose and listing filters efficiently. 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?

No output schema, so description must explain return values. It states returns list, total, unread count, which is adequate. It covers filtering and event types. Pagination is implied via parameters, but not explicitly described. Overall sufficient for a filtered list 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 coverage is 100%, so baseline is 3. The description adds value by listing event types explicitly and noting default/max for limit (默认 20，上限 100), which goes 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 '查询通知信箱' (query notification inbox) and specifies it returns a list, total count, and unread count. It mentions filtering by unread and event type, listing all event types. This clearly distinguishes it from siblings like get_messages or list_conversations.

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 does not explicitly state when to use this tool versus alternatives (e.g., mark_notification_read for marking). It implies usage for querying notifications with filters but lacks guidance on when not to use it or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.