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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety behavior is covered. The description adds useful behavioral detail by specifying inference rules for x/y columns, but does not describe the returned spec structure or how it relates to rendering.

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 two front-loaded sentences with no wasted wording. Purpose comes first, followed immediately by the useful inference behavior.

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 chart-spec builder with four parameters and no output schema, the description covers the essential call semantics but leaves gaps: it does not explain the return object shape, does not mention the mark default, and does not route between this tool and render_chart.

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 must compensate. It does so for the most ambiguous parameters x and y by explaining the inference fallback (first text/date column as x, first numeric column as y), and it identifies rows as result rows. Mark options and default come from the schema enum, so the remaining gap is minor.

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 states a specific verb and resource: build a minimal Vega-Lite chart specification from result rows. It clearly distinguishes the output from a rendered chart, but does not explicitly differentiate itself from sibling tools such as render_chart.

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 explains parameter inference but gives no explicit guidance on when to use this tool versus alternatives like render_chart. It implies usage by saying it builds a spec from result rows, but task-selection guidance is absent.

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