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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so the safety profile is covered. The description adds two valuable non-obvious behaviors: non-ChatGPT engines return not_applicable (never zero, preventing misread as 'no ads'), and ads are paid placements to be reported separately from citations/sources. It doesn't cover paging limits or auth needs.

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 core noun phrase, then the payload list, then the engine caveat, then the reporting warning. Dense parenthetical enumerations cost some readability, but every sentence carries 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?

With no output schema, the description does the heavy lifting by describing the returned content in detail, and the engine not_applicable rule plus the 'never as citations' caveat cover the main interpretive risks. The remaining gap is parameter-level semantics for a 7-parameter tool.

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 only 14% (just 'cursor'), yet the description never names or explains limit, cohort (core/comparison), engine, audit_id, or market_id. 'latest or a chosen run' and 'paged' faintly gesture at audit_id and cursor, but an agent gets no real semantics for 6 of 7 parameters.

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 ('Read ads in AI answers') and immediately enumerates the concrete payload: ad presence rate, advertiser share and first/last seen, brand ad share and best rank, text creatives, and surfacing prompts. This is clearly distinguishable from siblings like read_ai_shelf, read_ai_referrals, or read_visibility_sources.

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 real context for when it applies: 'for the latest or a chosen run' and the hard constraint that 'Only ChatGPT Search shows ads; other engines are not_applicable, never zero.' That engine rule is genuine when-to-use guidance. It stops short of naming an alternative sibling for non-ad questions.

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