plot_pair

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only mentions the output format ('JSON + inline PNG') but does not disclose that the operation is read-only, how sampling works, how 'top numeric columns' are selected, or any handling of missing data. This is insufficient for a tool that could be used on large datasets.

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 a single sentence, well front-loaded, with no wasted words. It conveys the core functionality and output format in a compact, efficient manner.

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?

The tool is relatively simple but still has ambiguities: what determines 'top' numeric columns, how sampling is applied, and what the JSON output contains are left unspecified. Given no output schema and no annotations, the description is not complete enough to allow an agent to invoke the tool with confidence, especially compared to the many similar plotting siblings.

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 has no parameter descriptions, and the description does not compensate. It does not explain the role of 'source_id', the meaning of 'sample', or the format/behavior of 'columns'. The only hint is 'top numeric columns', which loosely relates to the 'columns' parameter but is not explicit. The description adds no real meaning beyond the raw schema.

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 the specific phrase "N×N scatter matrix across top numeric columns" which clearly states the tool's function and distinguishes it from siblings like plot_scatter (single scatter) and plot_correlation_heatmap (heatmap). The verb is implied but unambiguous, and the resource is the numeric columns of the source.

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 implies usage for exploring pairwise relationships among numeric columns, but it gives no explicit guidance on when to prefer this over alternatives, nor does it mention any exclusions or when not to use it. It lacks explicit 'when to use' context beyond the inherent nature of a scatter matrix.

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