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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, and the description adds substantive semantics beyond them: what each mode covers, that replies and meetings count only people messaged in the period through now, the asymmetric window warning that last week's figures had 7 more days to arrive, and the rule that unreadable lines surface as unavailable rather than zero. That last clause is critical anti-hallucination guidance an agent could not derive from annotations or schema.

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 definition is front-loaded with the verb and resource, then the mode enumeration, then the caveats. It is denser than most but each sentence carries operational meaning; the 'never call a change in them a trend' clause is slightly editorialized yet still earns its place as methodological guidance.

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 two-parameter read-only reporting tool with no output schema, the definition covers what is generated, the time frame per mode, the timezone handling, and the counting semantics and data-quality caveats. What remains unstated is the response shape (since no output schema exists) and pagination or size expectations, though those are minor for an aggregate brief.

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 50%: 'timezone' is documented in the schema, but the 'kind' enum has no per-value descriptions there, and the description compensates by explaining what each of the four enum values produces. It also restates the timezone behavior ('in the user's IANA time zone', UTC fallback), which duplicates the schema rather than extending it. Baseline 3 is appropriate given the schema already documents the optional parameter.

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 verb (builds) and resource (the user's brief) and enumerates the four 'kind' modes with parenthetical explanations of each, which lets an agent distinguish morning from end_of_day from week_start/week_end without opening the schema. It stops short of differentiating this tool from any sibling in the large toolset, and no sibling is named as an alternative.

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 by the four mode descriptions, which tell the agent which kind produces yesterday-and-today, today-and-open, last-week-and-this-week, or week-over-week output. There is no explicit when-to-use vs. when-not-to-use guidance and no named alternative such as getAnalyticsReport or getOutreachAnalytics for related metrics, so the agent must infer selection from the mode semantics alone.

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