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

Beyond the readOnlyHint annotation, the description discloses key behaviors: the after-window is clamped to now, per-route pageviews are reported only if routes were recorded, and results may carry notes about truncated or uncovered windows. This goes well beyond the annotations and gives the agent actionable expectations.

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?

Three dense, front-loaded sentences convey purpose, window behavior, conditional details, timing guidance, and result-note handling without waste. Every sentence contributes meaningful operational information.

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 analysis tool with an output schema, the description covers the key semantics: window construction, clamping behavior, conditional per-route output, and how to handle result notes. The schema covers parameter details, so nothing essential is missing for correct invocation.

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?

The input schema already documents all parameters with 100% description coverage, including defaults and provenance of annotation_id. The description adds some context about how window_days relates to before/after windows, but most of this is already present in the schema, so the added value is limited.

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?

The description clearly states that the tool measures before/after impact of a recorded annotation in terms of visitors and pageviews. It is specific about the resource (an annotation) and the operation (comparing before vs after), though it does not explicitly differentiate itself from sibling tools like what_changed or query.

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 description gives clear contextual guidance: wait a few days after shipping, and relay any notes in the result by qualifying percentages accordingly. It does not explicitly state when to prefer this tool over alternatives, but the intended use case is strongly implied by the annotation-focused language.

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