aggregate_report

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds genuinely useful behavioral detail: results come back without 1000-row truncation, includes average resolution time automatically for task tables, durations are pre-formatted (with example '21 14:03:10'), and enumerates the full return payload (stats table, rows, count chart Adaptive Card, summary). This substantially exceeds the annotation baseline.

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 information-dense but front-loaded with the core distinction early. It packs many distinct pieces of value (no truncation, return types, format details, task-table behavior, array format flexibility) into a compact passage. Slightly long but every sentence contributes; no filler.

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 9-parameter aggregation tool with no output schema, the description is remarkably complete: it names all return components, explains the important task-table auto-average behavior, covers duration formatting, documents limit semantics, and contrasts against raw listing. Very little is left ambiguous for an agent considering this tool.

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 100%, so baseline is 3, but the description adds significant value: it explains avg_fields can be omitted for task tables to still get average resolution time, clarifies comma-separated strings are accepted for arrays, notes duration fields come pre-formatted, explains limit means 'top N groups by count', and gives an encoded query example format. This meaningfully enriches the schema-only understanding.

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 clearly states the tool performs server-side aggregate grouping by a field in one query without row truncation, computing per-group counts and stats. It distinguishes itself from siblings by explicitly noting it avoids raw record listing and compares against run_aggregate_query/trend_query/visualize_aggregate context.

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?

Explicitly says 'the right tool for a periodic summary like incident volume by category', gives concrete when-to-use guidance, and instructs 'Do NOT list raw records for this; use this', which clearly differentiates from list/query tools. Provides the example use case with avg_fields implication.

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