Read notifications

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context beyond annotations: the content scope, the 'newest first' ordering, and the guidance that 'mention' and 'reply' are the actionable types. This is meaningful additional context and does not contradict any annotation.

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?

Two compact sentences with no filler. The first sentence front-loads the core purpose and content scope, while the second delivers practical filtering advice. Every sentence earns its place.

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 read-only list tool with no output schema, the description together with the schema covers most essentials: content types, ordering, filtering, and pagination (via the 'limit' parameter description). It does not mention the 'account' parameter or when to use get_unread_count instead, but those are relatively minor omissions given the schema and annotation coverage.

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 80%, with the cursor parameter lacking a description. The main description adds semantic value by explaining the 'reasons' filter and singling out 'mention' and 'reply' as the ones requiring attention. This goes beyond the raw enum list, though the undocumented cursor remains a gap.

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 states a specific verb ('get') and resource ('notifications'), enumerates the exact content types (likes, reposts, follows, mentions, replies, quotes), and specifies ordering ('newest first'). It clearly distinguishes itself from siblings like mark_notifications_seen by describing a read operation and from get_unread_count by listing actual notification items rather than counts.

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 gives clear usage context: it returns all notification types and explains how to narrow to actionable ones via the 'reasons' filter, specifically identifying 'mention' and 'reply' as needing responses. However, it does not explicitly contrast with get_unread_count or mark_notifications_seen, so the agent must infer when those alternatives are more appropriate.

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