Account insights

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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds real behavioral context beyond that: a 30-day ceiling on the since/until window and preset-over-metrics precedence. It still says nothing about rate limits, pagination, or what the response looks like for each mode.

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 sentences carry a lot of information with no filler, but the leading "Account-level numbers." is weak and the long parenthetical enumerations are hard to scan. Structure is flat prose rather than grouped by preset mode vs. custom mode, which would read better for a 9-parameter tool.

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?

With no output schema, the description needs to carry return-shape information; it partially does by naming the fields each preset yields, but not the response envelope or how time_series differs from total_value. It also omits how this tool relates to nearby insight tools, leaving an agent to guess at boundaries.

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 coverage is 67%, and the description fills the biggest hole: the metrics array items are untyped strings in the schema, but the description enumerates every valid metric name. The preset-to-output mapping (overview, daily, reach_breakdown, follows) also adds meaning the enum list alone does not convey, though period and metric_type receive no elaboration.

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?

"Account-level numbers" plus an explicit inventory of the four presets and the customizable metric list makes clear this tool retrieves account-level insights rather than media-level ones. It implicitly separates itself from siblings like get_media_insights and get_audience by scope, though it never names them, and it lacks a real verb in the opening sentence.

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 does lay out two modes of use (pick a preset vs. supply your own metrics) and states that metrics is ignored when a preset is set, which is genuine routing guidance within the tool. It never says when to prefer this over get_media_insights, get_audience, or export_insights, nor does it state prerequisites such as a connected account or required scopes.

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