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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavior beyond them: data inclusion caveats (only prompts that took a click), authoring constraint (advertisers cannot write prompt text), what include_live actually returns (adExtensions opt-out records, not generated prompts), the absence of API-addressable IDs, and the US-only restriction. This is exactly the kind of context an agent needs and cannot get from annotations.

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?

Front-loaded with the definition, and nearly every sentence carries substantive information. It is dense and slightly long, with repeated '(verified 2026-10-09)' parentheticals and some duplication of the no-control point, but there is little pure filler.

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?

No output schema exists, yet the description enumerates the returned fields (impressions, clicks, CTR, CPC, cost, 7d/14d purchases and sales, CVR, ACoS), states the sort order (by spend), and covers the reporting window and constraints. Combined with the 12 documented parameters, an agent has everything needed to call it correctly.

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?

With 58% schema coverage, the description compensates by clarifying that asin is SP-only, that program spans SP and SB, what include_live adds (Ads API adExtensions records vs. generated prompts), and the date/window semantics ('over the window'). It leaves q, ad_group_id, campaign_id, limit and offset to the schema, so it is helpful but not exhaustive.

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 verb+resource and then defines what Sponsored Prompts actually are (conversational ads Alexa for Shopping / formerly Rufus, plus search and detail pages), the grain (per prompt x ad x ad group, SP and SB), and the metrics present. An agent can distinguish this prompt-level report from any other PPC reporting sibling without opening a 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?

Gives clear usage context: it's a reporting tool, only clicked prompts appear, only Amazon-authored prompts exist, and there is no API control (pausing is console-only, prompts cannot be edited/negated). It does not, however, name any alternative sibling tool or state when to prefer this over e.g. ppc_query or ppc_search_terms, so it stops short of explicit routing.

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