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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds real behavioral value beyond that: it discloses the comparative framing ('against the period before'), the trend granularity (daily or monthly), and the full inventory of returned breakdowns — useful context given there is no output schema. It says nothing about auth requirements, rate limits, or default period.

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?

Purpose is front-loaded and the single enumerated sentence, though long, earns its length by substituting for an absent output schema. The closing 'start here' sentence is short and actionable. No filler.

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 usefully compensates by describing the returned metric set and comparison window, and annotations handle the safety profile. The remaining gap is sibling routing: with umami_report, umami_realtime and umami_journeys in the namespace, it never says which one to prefer for a narrower or live-only question.

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% with every parameter individually documented (days default 28/max 730, limit default 10/max 50, optional website, start/end date format). The description mentions none of these, so it adds no meaning beyond the schema — the baseline 3 applies.

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?

States a clear verb+resource — 'Traffic at a glance from Umami for one website' — and enumerates the exact metrics and breakdowns returned (bounce rate, top pages, referrers, countries, devices, custom events, realtime visitors). It distinguishes itself from generic siblings through breadth, though it never explicitly contrasts with umami_report, umami_realtime, or umami_journeys.

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?

'Start here when the user asks how a site with Umami is doing or how many people really visited' gives a clear entry-point cue, but names no alternatives and no exclusions. This matters because umami_realtime appears to overlap with the 'visitors on the site right now' capability claimed here, and umami_report is never positioned relative to this tool.

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