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

Annotations already declare readOnly/idempotent/non-destructive, and the description's 'Reading changes nothing' largely repeats that. However it adds behavior the annotations cannot express: the default lookback window of the last quarter hour and the cursor-based incremental read via after/since, which is genuinely useful for an agent deciding how to poll.

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?

Every clause carries information, but it is delivered as one dense semicolon-chained sentence followed by fragments, which makes the key operational rule (pass after and since, else last 15 minutes) slower to extract than it needs to be. Front-loading the feed contents before the calling convention is reasonable.

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 no output schema, the description carries the burden of describing returns, and it does so reasonably: event categories plus ordering ('newest last'). Cursor semantics are covered. Minor gaps remain around volume/limits and what happens if after/since are mismatched.

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 description coverage is 100%, so the schema already explains key, after and since individually. The description restates the after/since relationship ('the after and now from the last call') rather than adding new syntax, units or edge-case handling, so the baseline 3 applies.

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 names the resource (news/events around you) and enumerates the concrete content: lines said to you or where you are, arrivals/departures, suggestions, invitations, proposals. An agent knows what it will get. It never contrasts itself with likely siblings such as inbox or digest, so it stops short of a 5.

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?

It gives a clear operating context — poll it while you wait — and explains the two modes (incremental with after/since, or default last quarter hour). It does not name alternatives (inbox, digest, pulse) or say when not to use it, so it lacks the explicit routing that would earn a 5.

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