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

Goes well beyond the readOnlyHint/destructiveHint annotations: it explains that conversion is completions/views computed as a whole percentage, that 0 views yields 0 rather than an error, that completions are not leads (announcement bars and ungated calculators complete without capturing an address), and that leads marked bad are excluded from figures. These are exactly the domain semantics an agent would otherwise misinterpret.

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?

Front-loaded with the returned totals, then metric definitions, then the optional date-range behavior. Dense but every clause carries information; the only mild cost is that lead/completion caveats are packed into long sentences rather than separated.

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 and a low-coverage input schema, the description carries the return-value burden and does so — listing default fields and the extra window/comparison, device, and UTM breakdowns returned with a date range. It stops short of describing ordering, limits, or how many items the breakdown lists can contain.

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 only 33% (only `project` is documented), so the description has to compensate — and it does: `from` and `to` are epoch milliseconds that must be supplied together, and supplying them changes the response contents. The `project` override is covered by the schema itself, so nothing is undocumented.

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?

Opens with a specific scope ("Totals for the current project") and enumerates the exact metrics returned (widget count, page views, completions, conversion %, leads, unsubscribes), so an agent knows precisely what it gets. It does not, however, distinguish itself from sibling tools like list_widget_analytics or read_widget_results, leaving the agent to infer that this one is project-level rather than per-widget.

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?

There is conditional guidance — "Pass from and to (epoch milliseconds, both) for a date range" tells the agent how to trigger the extended response — and a useful interpretation rule (0 means NO DATA, not failure). But there is no explicit statement of when to choose this over list_widget_analytics or read_widget_results, so tool selection is only implied.

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