Get Facebook Page Insights

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

The annotations already mark this as read-only and non-destructive, and the description does not contradict them. It adds behavioral context beyond the annotations by stating that meta_list_pages must be called first and that the return value is 'time-series data for each metric.' This gives the agent a clearer picture of dependencies and response shape than the annotations alone would provide.

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 opening sentence and prerequisite are front-loaded, and the Args section is logically organized by parameter. The long metric list is justified because the schema explicitly defers to the description for the complete list; it is a reference section rather than unnecessary repetition. Some minor redundancy exists with parameter names repeating the schema, but the added metric detail earns the length.

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 six-parameter tool with no output schema, the description covers the dependency, metric vocabulary, period values, date formats, and return shape at a functional level. It does not detail the exact structure of the time-series response, but no output schema exists and the schema handles response_format. Overall, an agent has enough context to call this tool correctly for page-level analytics.

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?

The schema covers response_format, period enums, defaults, and date formats, while the description adds substantial value by enumerating the full set of 70+ valid metric names and grouping them by category. It also clarifies that page_id is 'Facebook Page ID' and gives date formats for since/until. The only parameter not mentioned in the description text is response_format, but the schema adequately describes it.

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 that this tool 'Gets analytics/insights for a Facebook Page,' naming a specific verb, resource, and scope. This distinguishes it from sibling insights tools aimed at Instagram, posts, ads, campaigns, or ad accounts. The extensive metric list further clarifies exactly what kind of page-level analytics are returned.

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 gives a useful prerequisite: 'Requires: meta_list_pages called first.' However, it does not explicitly say when to prefer this tool over alternative insight tools, such as meta_get_post_insights or meta_get_instagram_account_insights. The intended usage is implied by the page-level resource and metric list, but exclusions and alternative routing are left to the agent to infer.

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