ads_keywords

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

With no annotations present, the description carries the full behavioral burden and does well: it explicitly declares 'read-only' and discloses the non-paginated 'returns every row' behavior. It also hints at why counts from this tool differ from console counts, which is useful operational context. It stops short of discussing auth needs or rate limits, but those are not critical for this read-oriented tool.

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?

Two sentence-length clauses with zero filler: the first states the resource and fields, the second explains the key behavioral difference from a console count. The 'read-only' safety hint is included without extra wording.

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 the presence of an output schema, two optional parameters, and a clear behavioral description, the tool definition is nearly complete. It explains return scale, read-only nature, and the status-omission behavior via schema. The only gap is the lack of explicit sibling routing, which is already penalized under usage guidelines.

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 the baseline is 3; the description itself adds nothing about the two parameters (days and status) beyond what the schema already documents. The schema descriptions are rich, particularly the status parameter's explanation of omitted-state behavior, so no additional compensation is needed.

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 states a specific verb ('Read') and resource ('every Google Ads keyword'), and enumerates the returned data (effective CPC bid, approval and serving status, metrics). The 'Returns every row rather than a first page' clause distinguishes this from sibling tools like ads_query or ads_campaigns by highlighting the full-fetch behavior.

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?

The description implies when to use the tool: when you need the complete keyword set and an accurate count, noting that console counts omit rows. However, it does not explicitly name alternative tools or state conditions for choosing this tool over siblings like ads_query or ads_search_terms, leaving the routing largely implicit.

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