Engagement

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

Annotations already establish the readOnly/idempotent/non-destructive safety profile, so the bar is lower. The description still adds real behavioral context the annotations lack: the range cap of 400 days, the constraint that 'to' is at most today, and the caveat that event names, paths, property values, sources and campaigns are raw visitor-supplied text.

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 most important sentence — what the report contains — is front-loaded, followed by sourcing/date constraints and then the raw-text caveat. Three short paragraphs, essentially no filler, though the raw-text note could be tightened.

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 carries the return-value burden and does list the report's components (entry/exit pages, single-page visits, duration median and buckets). It omits response format and pagination, but for a 3-parameter read-only report this is close to sufficient.

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 goes beyond the schema by adding the 400-day maximum range and restating the project-time-zone framing of dates, which the schema does not encode.

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 the specific contents of the report — top entry/exit pages, single-page visits (bounce), and visit duration with median and buckets — which is more than a restatement of the name. It does not, however, differentiate itself from nearby siblings such as 'visits' or 'overview', so an agent must infer the boundary.

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 only implied by the report contents. There is a useful prerequisite pointer ('The project id and the project's today come from list_projects'), but no explicit when-to-use-this-vs-alternatives guidance against siblings like visits, overview, or acquisition.

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