get_page_insights

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

Annotations are none, so the description carries full responsibility for behavioral disclosure. It reveals the permission requirement (read_insights), the exact endpoint used (GET /{page-id}/insights), and the structure of the metric parameter. It also implies that since and until are date boundaries for filtering the data. No annotations exist to contradict, but the description goes beyond basic info by clarifying prerequisites and parameter formatting, which is critical for an API call that might otherwise fail due to insufficient permissions.

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 the core purpose in the first line and the necessary usage details in the following lines. It is front-loaded with the action and resource. One minor issue is that the permission requirement is placed after the endpoint, but it is still early enough. The example metric list is valuable and not redundant. Overall, it is well-structured and efficient, though not perfectly minimal.

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?

Given the tool's moderate complexity (5 parameters, all optional, no schema descriptions) and the presence of an output schema (which covers return values), the description is largely complete. It covers prerequisites, metric formatting, period options, and the date range concept. The only gap is that it does not explicitly state default values or that all parameters are optional, but the schema shows defaults, so that is not a major issue. Thus, it is complete for effective use without excessive detail.

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 provides zero description coverage (0%) for the five parameters, so the description must compensate. It explicitly documents the metric parameter (comma-separated list, with examples) and the period parameter (allowed values: day, week, days_28, month, lifetime). It also implicitly explains since and until as date range filters via the endpoint path. It does not explain page_id, but that is a common identifier likely understood by the agent; overall, it covers the most complex parameters effectively.

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 Page analytics/insights (GET /{page-id}/insights)', specifying a verb (get), resource (Page analytics/insights), and the specific HTTP endpoint. It also provides concrete examples of metrics and periods, making the purpose unmistakable. While there are many sibling tools for page data, this one is uniquely about insights/analytics, so no confusion with siblings like get_page_posts or get_page_feed.

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 explains how to use the tool: it requires a Page access token with read_insights permission, and it explains how to format the 'metric' parameter (comma-separated list) and lists acceptable values for 'period'. It does not explicitly state when not to use it or mention alternatives, but the guidance is clear for common use cases. The context signals show no schema descriptions for any parameters, so this guidance is essential and well-placed.

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