meta get insights raw

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is fully covered by structured data. The description adds a small behavioral note about using 'validated native field names' and mentions pagination, but it does not disclose significant additional traits such as rate-limit implications, error behavior on invalid fields, or that the openWorldHint means the tool may accept unknown native fields. Given the strong annotation coverage, the description provides only marginal extra value beyond what annotations already state, so a 3 is appropriate.

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 exactly two sentences. The first sentence front-loads the core action and all major parameter categories, and the second sentence provides the crucial sibling-context. Zero filler or redundant restatement of the tool name. Every word earns its place and the structure leads with the most important 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?

Given the tool's complexity (14 parameters, nested objects, output schema present), the description is complete enough for an agent to decide whether to invoke it and what to expect in general. The output schema exists, so return-value documentation is not required from the description. The description covers purpose, scope, and the key differentiator from the curated tool. However, for such a complex raw API tool, a slightly richer note on how pagination works or how open-world field names are handled might improve completeness, but the schema and annotations already fill most gaps.

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% — every parameter has a meaningful description in the schema itself (e.g., fields: 'Native Meta Insights API fields; calculated aliases are not accepted here'; limit has bounds and default). The tool description only lists parameter categories ('breakdowns, action breakdowns, attribution windows, filters, sort, summary, and pagination') without adding specific semantics beyond what the schema already provides. Per the rubric, when schema coverage is high, the baseline is 3, and the description does not significantly raise 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 uses a specific verb ('Query') with a specific resource ('Meta Insights edge'), and enumerates the exact capabilities (native field names, breakdowns, filters, sort, summary, pagination). It also names the sibling tool meta_get_insights and draws a clear distinction: this tool is the raw-native-field counterpart to the curated metric catalog. An agent can immediately tell what this tool does and how it differs from the closest sibling.

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 an explicit use case: 'complements meta_get_insights when Meta adds fields before the curated metric catalog is updated.' This clearly identifies when to prefer this tool and names the alternative. However, it does not explicitly state when NOT to use this tool (e.g., 'if you need curated metrics, use meta_get_insights'), leaving the 'when-not' implicit rather than explicit. Also, no mention of other potential siblings like meta_list_edge_raw, though that is not necessary for a 4.

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