meta_ads_analysis_performance

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

With no annotations, the description carries the burden. It explicitly states 'Read-only' and describes what it returns (current/prior metrics, delta %, callouts), giving useful behavioral context beyond just the tool name. It lacks details on failure modes, but the read-only and output characteristics are well covered.

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 concise sentences in a logical order: purpose first, then output details, then usage guidance. No wasted words, and the callout examples make the output concrete.

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 tool with no output schema, the description explains what is returned (metrics, deltas, callouts), the period comparison logic, read-only nature, and when to use it. It is self-contained and complements the rich sibling context.

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 schema already documents period, account_id, and campaign_id clearly. The description adds minimal extra parameter meaning (e.g., 'or the whole account' implies omitting campaign_id), so a baseline 3 is appropriate.

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 it 'Produces an operator-ready performance review' with a specific verb and resource, and distinguishes itself from raw insights tools by focusing on 'period-over-period comparison' and callouts. This differentiates it from sibling tools like meta_ads_insights_report.

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?

Explicitly says 'Use this at the start of an audit' and directs to meta_ads_insights_report for raw insights, providing clear when-to-use and an alternative. This is strong usage guidance for an audit workflow.

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