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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the administrator-only constraint and the aggregation granularity, but says nothing about result size, pagination, or whether the window is inclusive — moderate added value against a lower bar.

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 compact sentence with the resource and breakdown front-loaded and no filler. Slightly dense in its trailing clause list, but every clause 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?

For a one-parameter, low-complexity tool with no output schema, the description usefully characterizes the return shape (calls and errors broken down by key, person, and tool) and the admin restriction. Only the ambiguity versus sibling AI/activity tools keeps it short of full completeness.

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% and the single 'days' parameter documents its range (1–90) and default (7) in the schema itself. The description only restates N as a day count and adds no format or edge-case detail beyond the schema, 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 a specific resource (AI connection use), a time scope (last N days), and the exact breakdown dimensions (calls and errors per key, per person, per tool), so an agent knows precisely what it returns. It does not, however, distinguish itself from close siblings like ai_activity_log or activity_summary, leaving the agent to guess which one to pick.

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 parenthetical '(administrators)' signals an audience/permission prerequisite, which is useful routing information. But there is no explicit when-to-use guidance and no mention of alternatives such as ai_activity_log for raw events or workspace_usage for aggregate usage, so selection between the AI/usage siblings remains implied at best.

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