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

With no annotations, the description carries the behavioral burden. It discloses that only metadata is returned and never conversation content, a key privacy trait. It also enumerates the valid group values beyond the schema. It doesn't explicitly state read-only, but the term 'statistics' strongly implies it.

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 description is three sentences: one for purpose, one for parameter domain, one for data nature, and one for examples. Every sentence adds value without redundancy, and the structure is front-loaded with the tool's purpose.

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 single-parameter stats tool with an output schema, the description covers purpose, parameter semantics, data scope, and usage guidance. It does not need to describe return values since the output schema exists. The description is complete enough for an agent to select and invoke correctly.

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?

The schema provides a bare string parameter with a default but no enum or description. The description fills this gap entirely by listing all valid group values and giving semantic examples ('who uses the most', 'busiest agent'), which are essential for correct invocation.

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 provides usage statistics, enumerates grouping dimensions (total, agent, user, space, day, model), and specifies that it returns token/event counts, distinguishing it from content-access tools. The usage examples imply a query action, making the purpose explicit.

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 explicit guidance on parameter selection ('Use group="user" to see who uses the most, group="agent" for the busiest agent'), which helps the agent choose the right grouping. However, it does not explicitly compare with sibling tools like page_context_stats, so there are no exclusion statements.

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