Retrieve total analytics metrics for a single website using a day count or ISO 8601 start/end range.
Totals for one website. Range: last days days, or ISO 8601 start/end.
| Name | Required | Description | Default |
|---|---|---|---|
| end | No | ||
| days | No | ||
| start | No | ||
| website_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| end | Yes | ||
| start | Yes | ||
| visits | Yes | ||
| bounces | Yes | ||
| visitors | Yes | ||
| pageviews | Yes | ||
| website_id | Yes | ||
| bounce_rate | Yes | ||
| total_time_seconds | No |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already covers the safety profile, and the description adds only the date-range window, which is mostly schema-level information. It says nothing about auth requirements, rate limits, or whether totals are scoped to a single site vs all sites beyond the vague "one website", so little behavior is disclosed beyond structured fields.
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?
Two short sentences, front-loaded with the resource and followed by the range rule; nothing wasted. Brevity is appropriate, though it is terse to the point of under-specification rather than sloppiness.
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 read-only tool with an output schema, return-value detail is not required, so the main gap is which aggregate is returned and how it relates to the sibling metric tools. Enough to invoke (website_id required, range modes given) but not enough to pick it with confidence among the umami family.
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 0%, and the description does clarify that `days` and `start`/`end` are alternative range modes (ISO 8601 for explicit dates) — valuable for two of the four parameters. It leaves `website_id` and the interaction rules (does `days` override `start`/`end`?) unstated, so it only partially compensates for the coverage gap.
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?
"Totals for one website" restates the tool name (stats = totals) without naming which aggregate is returned (visitors, pageviews, bounce rate?) or how it differs from the sibling umami_metrics. A verb-like framing exists but the resource is left ambiguous, so an agent cannot confidently pick this over umami_metrics or umami_pageviews.
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 only guidance is about date-range modes (days vs start/end), which is invocation mechanics rather than when-to-use. Nothing tells the agent in which situation this tool should be chosen over umami_metrics, umami_pageviews, or umami_websites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.