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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description redundantly states 'Read-only'. It adds minor context by listing the kinds of counters, but does not describe any additional behavioral details such as freshness, aggregation, or response shape.

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 a single concise sentence that front-loads the core purpose ('Service funnel counters') and includes the safety qualifier. No unnecessary words or repetition.

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?

Given the tool has no parameters, a simple read-only stats operation, and strong annotations, the description provides sufficient context. The listed counter categories make the purpose clear, though an explicit mention of the return format would make it marginally more complete.

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 input schema has zero parameters, so there is nothing for the description to clarify. The baseline of 4 applies because the description does not need to compensate for undocumented parameters.

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 identifies the tool as providing service funnel counters and specifies the kinds of data (page views, snapshots run, paid registrations). It is distinct enough from sibling tools like pw_health or pw_snapshot, though it does not explicitly name them as alternatives.

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 gives no guidance on when to use pw_stats versus the sibling tools. It states 'Read-only' but does not explain the intended use case or any conditions that would make this tool preferable to pw_health, pw_snapshot, or pw_watch_status.

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