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

With no annotations, the description fully explains behavioral nuances: by default it reads a pre-aggregated rollup for cheap wide-window queries, while the parent breakdown is computed on demand over raw spans and must be scoped. It also clarifies the returned metrics and percentage units, giving the agent a faithful model of what happens.

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 structured into clear sections: headline, usage guidance, parent-breakdown caveat, parameter list, and return shape. Every sentence adds value, and the examples are illustrative without being padded. It is appropriately detailed for a tool with six parameters and no output schema.

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 no output schema, the description fully enumerates the return fields (buckets, group, spanCount, errorRate, quantileNanos, queryStats, etc.). It also covers when to use the tool, how to scope expensive operations, and the meaning of all parameters, making the agent well-equipped to invoke it correctly.

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 already covers the parameters at 100%, and the description goes well beyond that with concrete formats and defaults: step units, 'omit for a single window', default groupBy of 'service, operation', and the semantics of parent_operation. This adds practical meaning beyond the schema's property descriptions.

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 action and resource: 'Aggregate spans into RED metrics: request count, error rate, throughput, and latency percentiles...' It clearly states what the tool computes and the grouping dimension. It also distinguishes itself from sibling raw-span tools by explicitly pointing to 'spans / get_trace' for drill-down after aggregation.

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?

It gives explicit 'START HERE' guidance for common questions ('where are errors / latency concentrated?', 'what changed between two windows?', 'is this operation slow?'). It names alternatives ('Drill into raw spans (spans / get_trace)') and warns that parent breakdown is over raw spans and should be scoped with tight from/to and filters.

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