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

Annotations already establish readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: the result is a decomposed attribution (CPC, conversion, mix, price), it can be enriched with matched ERP causes, and the agent must quote the returned numbers rather than recompute them — a real constraint on downstream behavior. It does not describe pagination or empty-result behavior, but for a read-only analytics call that is a minor gap.

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 sentences, zero filler. The metric scope and the output decomposition are front-loaded, and the quoting directive lands last where it will be read as an instruction on using the result.

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 eight optional parameters and no output schema, the description does the important work of saying what the response contains (effect breakdown plus ERP causes) and how to use it (quote, don't recompute). The main remaining gap is the interaction between the two period parameter pairs, which an agent must infer from the schema alone.

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%, with every parameter documented including defaults (acos, yesterday, 7 days ago, prior period). The description only reinforces that the tool operates across two comparable periods, which hints at how date_from/date_to interact with compare_from/compare_to but does not explain the pairing logic or the effect of supplying compare_to without compare_from. Baseline 3 is appropriate.

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 names a specific analytical operation (explaining a movement in ACoS, spend or sales between two periods) and enumerates the decomposition it returns: CPC, conversion, mix and price effects plus ERP causes. That is well beyond a restated title and clearly separates it from data-retrieval siblings like get_ad_performance. It stops short of naming a sibling to use instead, so a 4 rather than a 5.

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?

Usage is implied by the causal framing: call this when you need to know why a metric moved, rather than what it was. There is no explicit when-not guidance, no mention of what to do when no ERP causes match, and no pointer to get_ad_performance or get_ad_health as the alternatives for raw numbers or anomaly detection.

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