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

Annotations already declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds real value beyond that: it discloses the admin-only access requirement, the newest-first ordering, and the precise set of fields returned including error text and duration.

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?

A single dense sentence that front-loads the resource and scope, then enumerates the returned attributes without filler. Nothing is redundant and the ordering constraint appears early.

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 does the work of describing the return shape (key, owner, tool, success/error, duration, argument summary), and it flags the admin restriction. The remaining gap is that the seven optional filters are not tied to those described fields, but the tool is otherwise well-covered.

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 only 43%, so the description must carry more weight. It grounds the filterable dimensions by listing returned fields (key, owner, tool, worked/error, arguments), which maps loosely to key_id, user_id, tool, and status, but it does not explain filter semantics or the relationship between output fields and query parameters.

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 (AI connection activity in this workspace) and the exact events captured (tool calls and record reads), plus ordering (newest first). It is clear what the tool returns, though it never names a sibling like ai_usage_summary or workspace_activity to disambiguate.

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?

'(administrators)' signals the audience/permission context, which is useful, but there is no explicit when-to-use or when-not-to-use guidance and no routing to alternative activity/usage tools. Usage is only implied.

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