Tracking health

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

Annotations already cover the safety profile (readOnly=true, destructive=false, openWorld=true), yet the description adds genuinely non-obvious behavior: results are counts and sums only (no raw event records), the API is a preview build gated by AVADA_API_KEY, and failures must be surfaced rather than zero-filled. What is missing is any statement about default time window or how the response is organized.

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?

Front-loaded with the metric inventory, then constraints, then failure handling — a sensible ordering with no padding. The phrasing is telegraphic ('Counts and sums only'), which is efficient but occasionally reads as note fragments rather than prose.

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 does reasonable work by naming the report sections and clarifying the aggregate-only shape, plus documenting the auth requirement and the unavailable-case behavior. It remains incomplete for a metrics tool because nothing establishes the default reporting period or whether the sections are separately addressable.

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 single parameter 'days' has 0% schema description coverage, so the description carries the full burden of explaining it — but it says nothing about the lookback window, what happens if 'days' is omitted, or how the 90-day cap affects interpretation. Given a metric tool whose numbers are meaningless without a time frame, this is a meaningful omission.

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 enumerates the concrete contents (events by type, funnel, Conversions API delivery, purchases vs. real Shopify orders), which makes the scope of 'tracking health' concrete rather than tautological. It does not, however, position itself against the close siblings (account_overview, ads_breakdown, setup_status), so an agent must infer the distinction from the metric list alone.

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?

There is no guidance on when to reach for this tool versus measurement_get_account_overview or measurement_get_setup_status, and no stated prerequisites beyond the API key. The only conditional instruction is a failure-handling rule ('if it answers unavailable...'), which governs error reporting rather than tool selection.

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