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

Annotations only cover the read-only/non-destructive profile, and the description adds substantial behavior beyond that: the default window ends 3 days back because newer days are attribution-incomplete, impressions are ad impressions rather than search volume, and rows mix SP/SB. Those are exactly the traits an agent needs to interpret results 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?

The description is dense but front-loaded, with the core purpose first and caveats last. The parenthetical asides and the NOTEs make it slightly run-on, but every sentence contributes routing or interpretation value rather than restating the schema.

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 21-parameter, zero-required tool with no output schema, the description covers scope, returns, alternatives, and the key caveat well. It could go further on pagination expectations (next_offset) and on how SKU/ASIN/parent scoping parameters interact, which the schema leaves partly implicit.

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 71%, so most parameters are self-documented, and the description still adds meaning where the schema is silent: it frames the metric threshold filters as a group and explains the end_date override rationale (attribution lag). It does not clarify ambiguities such as start_date vs period_days or the two overlapping click filters (clicks_min vs min_clicks).

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 the specific resource (keyword/target bid performance), the exact ad types covered (rows carry ad_type SP/SB), and explicitly excludes SD targeting expressions by pointing to the ppc_query sd_targets dataset. It also enumerates the returned metrics and recommendation values, so an agent can identify the tool 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?

Names two concrete alternatives with the condition that selects each: SD targeting expressions belong to ppc_query/sd_targets, and organic search volume belongs to brand_sqp. It also states the default time window and how to override it, which is the routing decision most agents would get wrong.

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