meta_ads_analysis_compare_ads

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

The description declares the tool is 'Read-only' and explains outputs (verdicts: winner/laggard/insufficient-data). It also notes the period parameter's quota cost. With no annotations provided, this is sufficient behavioral disclosure, though it could mention that the tool does not modify any ads.

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 two sentences: first covers purpose and output, second gives usage guidance and companion tool. Every word adds value; no repetition or fluff. Excellent front-loading of key information.

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?

The description explains the full return structure (rows per ad, specific metrics, relative score, verdict) despite no output schema. It also notes read-only nature and statistical significance. Minor gaps: no mention of error handling or edge cases like a single ad in the set, but the 'insufficient-data' verdict partially covers this.

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% with detailed descriptions. The tool description adds context: ad_set_id is required because comparison is within a single ad set (same targeting/budget), and period notes that longer windows cost more Graph API quota. This goes beyond the schema's descriptions.

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 performs an A/B-style comparison of ads within a single ad set, ranking by efficiency and flagging winners. It specifies exact metrics returned (impressions, spend, conversions, CPA, CTR, relative score, verdict). This distinguishes it from sibling analysis tools like meta_ads_analysis_performance which are broader.

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 explicitly tells when to use the tool: 'Use this to decide which creatives to pause' and suggests pairing with meta_ads_ads_pause for action. It does not list negative cases or alternative tools, but the scope (single ad set) is clear, making inappropriate uses obvious.

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