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

With annotations already declaring readOnly/openWorld=false, the description still adds substantial behavior: ads stop at the latest Business Report date, ad_sales uses SP same-SKU 14-day attribution plus SD promoted-ASIN sales, total_attributed_ad_sales retains SP halo, organic_sales is derived by subtraction, and TACOS denominator differs from ASIN-level ACOS numerator. These alignment and attribution caveats are exactly the traps an agent would otherwise fall into.

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?

Purpose and data scope are front-loaded in the first sentence, then alignment rules and metric definitions follow in a logical order with no filler sentences. It is dense with jargon and metric-naming detail (e.g. the halo/compatibility note), which borders on overload for a description, but each sentence carries real 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?

Given 13 parameters at full schema coverage, an output schema, and non-destructive read annotations, the description supplies everything else an agent needs: grain options, window/alignment behavior, attribution definitions, and inclusion/exclusion rules. Nothing material for correct invocation is missing.

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 every parameter (including channel_split, group_by, include_zero_sales) is already documented in the schema. The description adds metric definitions rather than parameter-level meaning, so the baseline 3 applies.

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 opening sentence states a specific resource (ASIN-level TACOS/PPC share) plus its data provenance (Business Reports + aligned SP/SD product data), and the closing sentence carves out the sibling grain it is not ('Use campaign tools for campaign ACOS'). An agent can distinguish this from campaign- and SB/DSP-level tools without opening the schema.

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?

It gives clear selection context: use this for ASIN-level TACOS/PPC share, and it explicitly excludes Sponsored Brands and DSP while redirecting campaign-level ACOS needs to campaign tools. The alternative is named only generically ('campaign tools') in the body rather than by a concrete tool name, and no prerequisites (auth/account scope) are stated.

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