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

Adds real context beyond annotations: results are limited to a single page and to US desktop inventory, punctuation is preserved verbatim, nulls carry missing evidence, and the data is provider observation rather than verified account performance. It does not disclose rate limits or how to obtain further pages, but that is a minor omission against otherwise strong caveat coverage.

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?

Four short clauses, scope first, caveats after; no filler sentences. The telegraphic style occasionally costs clarity, but nothing is redundant.

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 and no parameter documentation, the description should carry the load. It does convey evidence caveats and nullability, but return-shape expectations and the meaning of the two inputs remain unstated, leaving the agent unable to fully predict results.

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 0%, so the description must explain both parameters. It never says what 'keyword' matches or that 'limit' (1–20, default 10) caps rows within the single page — 'single page' only hints at it. The schema's defaults and maximums stand unexplained.

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 identifies a specific resource — paid search ad samples — with scope qualifiers (single page, US desktop) that make it distinguishable from generic keyword or ad-transparency siblings. The retrieval verb is only implied by the noun 'samples', and no sibling is named to route the agent away, so it stops short of 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?

'No additional calls or fallback' is a constraint on execution, not a when-to-use rule; it does not tell the agent which sibling to pick (e.g. ad_transparency_search or paid_keywords) or when this tool is the wrong choice.

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