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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: default time window and timezone, data_status distinguishing true zero from missing data, the non-additivity of unique counts across days, 'unknown' platform semantics, attribution caveats to surface, and explicit statement of what is NOT measured (bots, citations, AI campaigns). This is exactly the caveat-level context an agent needs to interpret output correctly.

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 purpose and scope, then moves through arguments, data interpretation, and measurement limits. Dense but nearly every clause carries operational information; a couple of caveat clauses could be consolidated, but there is 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?

An output schema exists so return structure needn't be described, and the description covers what remains: defaults, timezone, metric scope, comparison behavior, data-quality semantics, and explicit measurement gaps. An agent can call this tool and interpret its result without further context.

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 80%, so the baseline is 3; the description earns above that by explaining the relationship between parameters — period supersedes date_from/date_to, and compare=previous_period compares equal-length windows. It adds decision guidance rather than repeating the schema, though it does not cover the breakdown parameter.

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 specific resource and scope: AI traffic analytics from Matomo, aggregates only, with named metrics (visits, actions, unique AI users, platforms, orders). The verb/resource pairing is unambiguous and no sibling tool covers anything similar, so no sibling differentiation is required.

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?

Gives concrete invocation guidance: with no arguments it reports yesterday in Europe/Warsaw; use period last_1/last_7/last_30 instead of explicit dates; compare=previous_period to compare against the prior window. It also tells the agent which field to read platform names from (by_provider) and warns not to sum uniques across days, though it never explicitly contrasts usage against an alternative tool.

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