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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the term 'bounded', which hints at a limit on results, but this is also implied by the 'limit' parameter in the schema. No additional behavioral context (e.g., pagination, aggregation details) is provided, and there is no contradiction with annotations.

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 two sentences and stays under 30 words, with the main action front-loaded ('Return bounded...'). It is concise and readable, though the list of metrics in the first sentence is a bit dense but still efficient.

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 should explain what the response contains; it lists the metrics (visits, actions, bounce rate, etc.) but does not describe the response format or how the data is structured (e.g., rows per referrer). It also omits guidance on the 'segment' parameter and the meaning of 'bounded' relative to 'limit'. While the purpose is clear, an agent would need to infer several details about parameters and output.

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 71% (5 of 7 parameters have descriptions), but the missing descriptions for 'limit' and 'period' are not compensated by the tool description. The description only mentions 'bounded' without explaining how to control it via the limit parameter, and it does not clarify the role of period or segment. Since coverage is below 80%, the description should have provided more parameter context but does not.

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 a specific verb ('Return') and a concrete resource (acquisition categories, sources, visits, actions, bounce rate, conversions, revenue), and clarifies the purpose ('Answers which channels and referrers drove valuable traffic'). It clearly differentiates from sibling tools like matomo_goal_performance or matomo_visit_summary by enumerating the exact metrics returned.

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 the purpose statement ('Answers which channels and referrers drove valuable traffic'), which tells an agent when this tool is relevant. However, there is no explicit guidance on when not to use it or how it compares to alternatives like matomo_page_performance or matomo_goal_performance, so the guidance remains implicit rather than explicit.

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