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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: per-account-per-UTC-day row granularity, a 92-day range cap with a 30-day default, and an explicit privacy guarantee that no message text or recipients are returned.

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?

One dense but front-loaded sentence leads with row granularity and range rules before listing metrics, followed by a short privacy note and endpoint reference. The parenthetical enumeration of action types is long but each item is informative; nothing is redundant filler.

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 correctly enumerates the returned columns and notes the JSON format via the endpoint reference, and it covers both optional parameters and their defaults. It is complete enough to call correctly, with only minor gaps such as how the row set behaves for accounts with no activity in a day.

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 0% and the schema only supplies a date pattern, so the description carries the full burden — and does: both from and to are YYYY-MM-DD, inclusive, capped at 92 days, defaulting to the last 30 days. That fully compensates for the bare schema and even explains the schema's $ref relationship implicitly.

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 states the resource and granularity precisely: "One row per account per UTC day" with an enumerated set of metrics (messages_sent, new_chats, actions by type), and identifies the underlying endpoint GET /v1/messaging/usage/export?format=json. It does not explicitly contrast itself with the sibling get_messaging_usage, so the export-vs-report distinction is left to the name.

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?

Usage is implied through constraints (inclusive from/to, at most 92 days, default last 30 days) rather than stated as when-to-use guidance. There is no explicit statement of when an agent should pick this over get_messaging_usage, and no exclusions or prerequisites are given.

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