discover_keywords

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds significant behavioral context: results sorted by avg monthly search volume, includes competition level and bid range, default page size, and max page size. No contradiction with 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?

The description is well-structured with a clear lead sentence, then bullet-style explanation of modes, return values, and parameters. It is not overly verbose, but could be slightly more concise (e.g., the parameter details could be formatted more tightly). Front-loaded with purpose.

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 tool has 6 parameters and an output schema, the description covers the tool's purpose, modes, and key output fields. It explains most parameters and provides examples. The only gap is customer_id not being described. The output schema likely covers return structure, so no further detail needed. Overall sufficient for an agent to invoke 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?

Schema description coverage is 0%, so the description must compensate. It explains seed_keywords, url, geo_target_id, language_id, and page_size with examples and defaults/limits. However, customer_id is not mentioned in the description, leaving a gap for that parameter. The description adds meaning for most but not all 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?

The description clearly states the tool discovers keyword ideas using Google Ads Keyword Planner. It distinguishes itself from sibling tools like 'draft_keywords' and 'get_keyword_performance' by focusing on keyword discovery, not drafting or performance metrics. The specific verb+resource combination and mention of two modes (keywords and/or website) provide high clarity.

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 explains when to use each parameter combination (seed_keywords, url, both). It mirrors the UI and provides examples for geo and language. However, it does not explicitly state when not to use this tool or mention alternatives like 'draft_keywords' for negative keywords, though the context of sibling tools makes it implicit.

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