get_summary

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

With no annotations, the description must carry the full burden. It discloses per-minute aggregation over a single calendar day, timezone default, raw=True behavior, no numeric rounding, and the non-error behavior for unsupported drilldown combos. This is rich, truthful context beyond any structured metadata.

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 longer than average but well-structured with line breaks, bullet-like sections, and a logical flow from stats to time selection to timer to drilldowns to raw mode. Every sentence adds value; the length is justified by the 18-parameter complexity and lack of annotations.

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 complex tool with no annotations and zero schema descriptions, this description covers time selection rules, timer choice, percentile range, drilldown behavior, raw mode, timezone, aggregation granularity, and error behavior. Since an output schema exists, return values are already documented, so the description doesn't need to over-explain them.

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 0%, so the description compensates by explaining key parameters: date, date_comparator, timer/custom_timer, percentile, raw, and several drilldowns (page_group, browser, country, device_type, ab_test). It does not explicitly explain every parameter (e.g., os, region, connection_type), but the pattern and examples provide enough guidance for most.

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 opens with a specific verb+resource: 'Aggregate summary stats for one timer (median, margin-of-error, count, p95, p98).' This clearly distinguishes it from siblings like get_histogram and get_metrics by naming the exact aggregate outputs and the 'one timer' scope.

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 explicitly states that exactly one time selector (date or date_comparator) is required, that date ranges are unsupported and must be split into per-day calls, and that drilldowns filter data with unsupported combinations returning empty data + note instead of an error. This gives clear when-to-use and constraint guidance.

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