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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive), and the description adds real value beyond them: how buckets are formed, that the comparison is impression-weighted, that negative deltaPoints signals a title/meta issue, and that `reliable` marks buckets with sufficient impressions. It stops short of describing the response shape or how sparse buckets are handled.

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?

The core computation and interpretation are front-loaded in a single dense sentence, followed by a short usage cue. The trailing bilingual echo ("/ Curva de CTR própria × benchmark.") duplicates the title and is the only wasted text.

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 11 parameters, no output schema, and an interpretive metric, the description does the essential work: it defines deltaPoints and `reliable`, names the benchmark reference, and gives the analytical intent. What is missing is only the shape of the returned curve rows.

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 100%, so the baseline is 3. The description's mention of impression-weighted bucketing and the `reliable` threshold loosely restates what the `minImpressions` schema field already documents, adding little new parameter-level meaning.

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 computation: the property's real CTR by position bucket (round(position), 1–20, impression-weighted) compared against a generic benchmark. An agent knows exactly what it gets. It does not, however, differentiate itself from the sibling get_ctr_benchmark, which sounds closely related.

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?

"Use to find where titles underperform" gives a concrete diagnostic context, and the deltaPoints explanation (negative = below expected: likely title/meta problem) reinforces when this tool is the right pick. No explicit when-not guidance or named alternative (e.g. get_ctr_benchmark) is offered.

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