google_ads_keywords_audit

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

States 'Read-only — recommendations are not applied', disclosing the non-destructive nature. Describes output structure including attributes like criterion_id, text, spend, etc. No annotations provided, so description carries the full burden. Could mention rate limits or permissions, but acceptable.

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 sentences with no wasted words. First sentence defines purpose and output groups; second sentence details item attributes and next steps. Front-loaded and efficient.

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?

Despite no output schema, the description thoroughly explains the return value (grouped recommendations with fields). It mentions how to use the results via sibling tools. For a simple audit tool with 4 params, this is nearly complete. Could specify exact output shape or that it's per campaign, but sufficient.

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 100%, so baseline 3. The description does not add additional parameter-level details beyond the schema. It focuses on output and behavior, not parameter semantics.

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 explicitly states 'Runs a holistic keyword-portfolio audit for a campaign and returns grouped recommendations' with specific recommendation types (pause, bid-raise, etc.). It clearly distinguishes from sibling tools that modify keywords.

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?

It mentions to 'Materialize accepted ones via google_ads_keywords_pause / add / negative_keywords.add', guiding the agent on next steps. It lacks explicit when-not-to-use but the read-only nature and context imply usage for auditing only.

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