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

Annotations already establish the safe-read profile (readOnly, non-destructive, idempotent, closed-world), and the description adds real context beyond that: the Asia/Taipei day boundary, that days=1 means today since 00:00, the ordering (newest first), and cursor-based paging. It does not mention rate limits, retention, or behavior when no calls exist, which keeps it from a 5.

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 scope constraint and return shape are front-loaded, and parenthetical field lists pack a lot into a compact sentence pair with no filler. It is dense to the point of being slightly hard to scan, but nothing is redundant.

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 return-value burden itself and does so fully: it names both result sections and their fields, the sort order, pagination mechanism, and record scoping. An agent can construct the call and interpret the response without further information.

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 100%, so the baseline is 3; the description earns an increment because it clarifies the timezone basis of the `days` window ("today since 00:00 Asia/Taipei"), which the schema's "1-30 (default 1 = today)" leaves ambiguous. `limit` and `cursor` are only restated, not elaborated.

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?

Specific verb ("Returns") plus a precisely scoped resource ("this connection's own usage") and an enumeration of what comes back (summary: calls, units, errors, by_endpoint; recent calls: request_id, endpoint, status, units, at). "Only this connection's records" separates it cleanly from account-wide siblings like analytics_insights, cloud_patrol_stats, or list_events.

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?

Explicitly states applicability: "when the user asks what this connection did, or a request_id is needed to report a problem." That is a concrete triggering condition rather than an implied one. It does not name a competing sibling or a when-not condition, so it stops short of a 5.

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