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

Annotations already cover readOnly/idempotent/openWorld, so the bar is lower, and the description still adds context: the shape of the return (flat ranked candidates plus a tier/ad-group/match-type/bid-strategy recommendation) and a hard prerequisite (pre-resolved geo + language constants).

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?

Purpose is front-loaded, followed by return shape, workflow role, and prerequisite. The em-dash clause is slightly discursive but every sentence carries information; nothing is filler.

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?

For a 9-parameter tool with no output schema, the description helpfully explains the return payload and the constant prerequisite, but several seed/control parameters (positive/negative keywords, isBrandedCampaign) remain undefined, leaving an agent guessing on meaningful inputs.

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 22% across 9 params, so the description must compensate. It gives meaning to landingPageUrl, dailyBudget, and the two pre-resolved constants, but leaves positiveKeywords, negativeKeywords, isBrandedCampaign, maxKeywords, and brandId entirely unexplained in both schema and description.

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?

Specific verb (Discover) + resource (Google Ads keywords) + scope (for a landing page, ranked by ROI, budget-filtered). It explicitly carves out what it does versus what the caller must do, and reads distinctly from siblings like generate_campaign_draft or fetch_keyword_forecasts.

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?

Clearly frames the workflow boundary: the tool performs deterministic discovery and budget-aware structuring, while the LLM caller does thematic grouping and ad-group naming with the user. No sibling alternative is named or explicitly excluded, so it stops short of a 5.

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