visualize_aggregate

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description reinforces this with 'Read-only.' The description adds value by disclosing the multi-format output (chart data, Adaptive Card for Copilot Studio, markdown table, summary), which is behavioral context beyond the annotations. It doesn't detail pagination or the 'real-time' refresh behavior, but with two annotations covering the safety profile, this is adequate.

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, front-loaded with the core purpose and concrete examples, then output formats in a compact list. Zero wasted words. The 'Read-only' label is a useful single-word note at the end.

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 tool with full schema coverage (100%), complete annotations (readOnlyHint, openWorldHint), no output schema, and no nested objects, the description thoroughly covers the tool's purpose, output formats, and integration target (Copilot Studio). The examples for table and group_by values in the schema complement the description well. Nothing material is missing.

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 100%, with every parameter (table, group_by, query, limit, title, chart_type) having meaningful descriptions in the schema. The description adds the default chart_type ('column') implicitly via schema and clarifies that table examples are provided in the schema. The description itself does not go beyond the schema's parameter docs, so the baseline 3 for full coverage is appropriate.

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 uses a specific verb+resource: 'Build a real-time chart of ServiceNow records grouped by a field' with concrete examples (incidents by priority, cases by state). It clearly distinguishes from related siblings like visualize_trend (trend-over-time) and run_aggregate_query (raw SQL aggregation without visualization) by emphasizing chart-ready output. The read-only nature is stated explicitly.

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 clearly states what it returns (chart data, Teams Adaptive Card, markdown table, summary) which indicates when to use it over alternatives like run_aggregate_query or trend_query. However, it does not explicitly name sibling tools as alternatives or state when NOT to use it (e.g., when you need raw data only, or want time-series trends). The 'Read-only' tag gives some usage context via annotations.

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