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

Annotations already declare readOnlyHint: true and idempotentHint: true, so the safety profile is established. The description adds value by revealing the data scope ('views, starts, submissions') and explicitly documenting the open-ended date range behavior (dateFrom only, or dateTo only), a non-obvious edge case an agent would likely get wrong. It loses one point for not disclosing behavior on invalid entityIds or response shape etc., though these are less critical for a read-only tool with no output 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?

Two sentences, zero redundancy. The first sentence front-loads the tool's purpose, and the second covers all the date combination scenarios. Every phrase earns its place. No repetition of what the schema already documents — the description focuses on the behavioral add-ons.

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?

The description thoroughly covers the date behavior for a 4-parameter tool with 100% schema coverage and read-only annotations. Since there's no output schema, one could argue the response format should be described to fully close the loop — the description says it returns 'aggregated statistics (views, starts, submissions)' but not their structure. This is a minor gap for an otherwise well-specified tool.

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's extra value comes from explaining the relational semantics between dateFrom and dateTo that the schema describes individually but not combinatorially. Specifically, the sentence about 'only provide one of them for an open-ended date range' adds meaning beyond the schema's individual parameter descriptions, so I'm bumping this to a 4.

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 clearly states the tool 'Returns aggregated statistics (views, starts, submissions) for a single period.' The verb+resource is specific and easily understood. While the 'single period' phrase implicitly differentiates from siblings like stats_overview_fetch and stats_*_breakdown, it doesn't explicitly name or contrast against them, which costs it a point toward a 5.

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 description provides excellent, actionable guidance on parameter combinations: 'Omit dateFrom/dateTo for alltime stats, provide both for a specific date range, or only provide one of them for an open-ended date range.' This is clear when-to-invoke context for the edge cases. However, it never discusses how this tool compares to the sibling breakdown/overview stat tools, so an agent might not know when to choose this variant over stats_project_breakdown or stats_user_breakdown.

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