Read notifications

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds ordering (newest first) and the actionable-reason heuristic, but says nothing about pagination behavior or auth needs beyond what the schema provides. Reasonable but not rich.

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 sentences, front-loaded with the resource and ordering, followed by the filtering heuristic. Slightly informal ('a person actually has to deal with') but no real waste.

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 exists, but the description conveys what is returned (notification types, newest first) and how to narrow results. Combined with annotations covering safety and a schema that documents pagination and account selection, it is largely complete; missing explicit mention of pagination or unread filtering.

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%, so the baseline is 3. The description adds semantic value by indicating which 'reasons' enum values are most actionable ('mention', 'reply'), which is meaning beyond the raw enum list. It does not address limit, cursor, account, or unread_only.

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 resource (notifications) and its scope: likes, reposts, follows, mentions, replies, quotes, newest first. An agent can identify it as the notifications reader. It does not, however, distinguish itself from siblings like get_unread_count or mark_notifications_seen.

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?

Offers actionable guidance on filtering: use 'mention' and 'reply' to surface items that need an answer. That covers a key usage pattern, but there is no statement of when to use this tool versus get_unread_count or mark_notifications_seen, so the routing guidance is incomplete.

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