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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the description's added value is the plan-eligibility caveat — that current plans yield no overage rows at all — which is genuinely useful behavioral context not available anywhere else. It does not cover pagination or result-count behavior, which keeps it below 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?

Two sentences, no filler: the scope and its caveat come first, the sibling contrast second. The literal endpoint path is the one technical flourish and it earns its place by making the aggregate-vs-ledger contrast concrete.

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?

An output schema exists, so return values need no explanation, and the definition covers the critical scoping caveat plus the sibling relationship. The remaining gap is guidance on the optional filters (status, date range), which the low schema coverage leaves under-documented across both fields.

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 only 20%, so the description would need to carry more weight: it explains nothing about from/to range semantics, limit, status filtering, or business_id scoping. Schema coverage of 20% (with only business_id documented) leaves four of five parameters unexplained. The phrase 'per-period ledger' only faintly implies a date-range concept. A baseline of 3 for adequate-but-thin parameter meaning, rather than a penalty to 2.

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 verb and resource — 'List the per-period overage-minutes ledger' — and immediately contrasts it with get_balance, which 'only returns an aggregate' while this returns 'the underlying per-period ledger rows'. An agent can tell exactly what it retrieves and how it differs from the nearest sibling.

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 '(older per-minute-overage plans only; current plans carry no overage)' is an explicit when-not signal that prevents wasted calls on current plans, and naming get_balance's aggregate behavior implies the routing rule for the alternative. What is missing is a direct imperative ('use this when you need per-period detail'), leaving the choice slightly inferential.

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