plot_distribution

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

With no annotations provided, the description carries the full burden and does an excellent job. It discloses server-side binning for numeric columns, top-50 value counts for categorical columns, the return format (structured JSON + inline PNG as MCP ImageContent), and the reliability benefit of single-image responses. This is rich, useful behavior information beyond what any schema could convey.

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 tightly written: three sentences, each earning its place. The first sentence front-loads the core purpose, the second details behavioral nuances, and the third provides client-compatibility guidance. No fluff or repetition.

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 the tool's moderate complexity (multiple plot types, output format) and the absence of an output schema or annotations, the description covers the essential points: what it does, how numeric vs. categorical columns are handled, what the return includes, and when to prefer it over an alternative. It lacks some edge-case details (e.g., behavior for mixed columns), but it is sufficiently complete for most agent decision-making.

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 explains that 'columns' can be a single column or multiple, and it touches on binning behavior which relates to the 'bins' parameter, but it does not explicitly describe the 'bins' parameter's effect or the meaning of 'source_id'. The description adds some meaning but leaves gaps for two of the three parameters.

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 crisp, specific purpose: "The right tool to answer 'show me the distribution of X'" and explains the single-column vs. multi-column behavior. It also distinguishes itself from a sibling by explicitly naming eda_storyboard as the alternative for focused per-column questions. This clearly states the tool's unique role.

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 provides explicit guidance on when to use this tool: for focused per-column distribution questions, and even directs users to prefer it over eda_storyboard. It implies broader explorations would use eda_storyboard, but it doesn't explicitly state all exclusions or other alternatives, so it falls just short of full when/when-not coverage.

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