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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety needs no restating. The description adds genuinely useful behavior: the window is fixed and non-negotiable, timestamps are UTC, and the payload is per-hour metrics — preventing an agent from attempting date parameters.

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, no filler, with the window and grain front-loaded and the exclusion clause last. Every fragment earns its place.

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 two-parameter read tool with annotations and no output schema, the description covers grain, window, timezone, and the metric set. The residual gap is the undocumented required `site` argument and whether filters narrow all metrics uniformly.

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 50% and the required `site` parameter has no description in either the schema or the description text. The only parameter-adjacent content is the negative statement 'no days/from/to'; the rich nested `filters` semantics live entirely in the schema, so the description contributes essentially nothing here.

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?

Names the exact resource and grain — hourly buckets over the last 24 hours — and enumerates the returned metrics (visits, visitors, pageviews, clicks, bots). The clause 'Fixed window, no days/from/to' implicitly separates it from range-taking siblings like get_timeseries and get_stats, though it never names an alternative outright.

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 fixed-window constraint implies when this tool applies (quick last-24h view) versus range-based tools, but no sibling is named and there is no explicit 'use X instead when you need Y' guidance. The agent must infer the routing from sibling names alone.

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