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

The readOnlyHint annotation already covers the safety profile, and the description adds context about event categories and the cursor-based 'since' behavior. It does not disclose ordering, pagination, deduplication, or retention behavior, but the annotation lowers the bar for read-only tools. The description does not contradict the 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?

The description is a single sentence that front-loads the tool's purpose and then provides the key usage instruction. It has no filler and communicates the core idea quickly. It loses one point because the parenthetical list of event categories and the 'since' guidance are packed together rather than structured, making it slightly less scannable than it could be.

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 simple read-only feed tool, the description covers the main purpose and the most important parameter behavior. But since there is no output schema, the event object structure is not described, and the 'limit' parameter's effect on results is not explained. The agent can likely call the tool correctly, but some runtime behavior remains underspecified.

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?

Only the 'types' parameter has a schema description, so schema coverage is low at 33%. The description adds valuable meaning to 'since' by clarifying it is a last event id rather than a timestamp. However, the 'limit' parameter semantics are left undocumented in both the schema and description, and 'types' behavior is only minimally explained despite the schema examples.

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 frames the tool as a personal activity feed: 'Everything that happened to me (jobs, payments, messages, reviews)'. It identifies the resource and broad event categories. It stops short of a 5 because it never uses an explicit retrieval verb like 'list' or 'get', and it does not strongly distinguish itself from sibling tools such as 'feed' or 'inbox'.

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 a concrete usage tip: 'Pass since=<last id> to get only new ones', which is helpful for incremental polling. However, it does not explicitly say when this tool should be preferred over alternatives like 'feed' or 'inbox', nor does it state exclusions. Usage is implied by scope rather than explicitly contrasted.

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