get_insights

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

Annotations already declare readOnlyHint and idempotentHint. Description reinforces read-only use and adds details on returned fields (spend, delivery, click, etc.), without contradicting annotations. Adds moderate value beyond 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 concise with a clear structure: single-sentence summary, then Args, Returns, and usage guidance. No redundant sentences; every part adds value.

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?

Covers purpose, parameters, return format, and usage boundaries. The output schema exists and is described in the Returns section. Sibling tools are listed but not explicitly contrasted, though usage guidelines imply differentiation. Overall complete for a flexible read-only tool.

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?

Despite 0% schema description coverage at the top-level, the description lists all key parameters (Object ID, level, date preset/range, limit, format) and summarizes their roles. The nested schema provides individual descriptions, so the description adds a helpful high-level view.

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 'Get raw Meta performance metrics for an object and reporting period', specifying the verb, resource, and context. It also mentions the available levels (account, campaign, ad-set, ad), which helps distinguish it from sibling list tools like get_campaigns.

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 for flexible read-only metric retrieval' and warns 'Do not use it to modify delivery or to infer causal lift', providing clear when-to-use and when-not-to-use guidance that differentiates from siblings.

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