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

Annotations already establish readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact beyond the annotations: '(administrators)', i.e. an elevated-permission requirement. It says nothing about rate limits, freshness, or whether data is aggregated or sampled.

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 front-loaded sentence names the scope, the time window, the permission gate, and the breakdown dimensions with no filler. Nothing could be removed without losing 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?

There is no output schema, so the description correctly compensates by stating what the result contains (calls and errors per key, per person, per tool). It does not explain return shape (e.g. totals vs. time series) or list the sibling tools it competes with, leaving a small gap for a single-parameter administrative report.

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 parameter already documents its bounds and default ('1–90, default 7'). The description's 'last N days' only restates the same window semantics without adding format, edge-case behavior, or default-handling guidance. 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 (AI connection use) and its aggregation dimensions (per key, per person, per tool), which clearly distinguishes it from sibling ai_activity_log's event-level logging. It lacks a stated verb, but the noun phrase is specific enough to identify the operation. No sibling is named explicitly for contrast.

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?

There is no when-to-use guidance and no reference to the nearby alternatives (ai_activity_log, list_ai_connections, workspace_usage). The only scoping signal is the implied 'over the last N days' window. An agent must infer the use case entirely from the noun phrase.

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