activity_stream_summary

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

The annotations already declare readOnlyHint=true, non-destructive, and openWorld, so the safety profile is covered. The description adds genuine context beyond that: it is an aggregate count rather than a listing, it is explicitly a cheap call, and it names the concrete payload shape (unread_count plus total per type). It does not discuss data freshness or caching, which is the only notable gap.

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?

Three short sentences, front-loaded with the core definition, then the payload shape, then the usage hook. No filler or repeated framing; every sentence carries information.

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?

With zero parameters, full annotations, and an output schema already documenting return values, the description only needs to explain what the aggregate represents and when to reach for it, which it largely does. The missing piece is an explicit contrast with activity_stream and whats_new, which share this tool's territory.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. It correctly focuses on describing the output semantics instead of inventing parameter guidance.

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 gives a specific verb-and-resource pairing: 'aggregated unread counts by notification type,' and enumerates the actual types (Announcement, DiscussionTopic, Submission, Message, Conversation). It is clear what the tool returns, but it never names the sibling it differs from (activity_stream, whats_new), so an agent must infer the distinction itself.

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?

'Great for what changed since last check' implies a use case, and 'cheap call' signals it is a low-cost first probe. However, there is no explicit when-not guidance and no mention of alternatives such as activity_stream for item-level detail, leaving the routing decision implicit.

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