run_eda

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

With no annotations provided, the description fully carries the transparency burden. It discloses the return format, output size (small, top-10 findings), side effect (full results written to artifact), and the conditional behavior that temporal checks only run when hints.time_column is provided. This gives an agent a solid behavioral model before invoking the tool.

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 efficiently structured with a concise opening sentence followed by scannable bullet points for presets and hints. Every sentence adds value: preset levels, runtime estimates, conditional temporal behavior, hint keys, and output size. There is no filler or repetition of schema information.

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 description is complete for a tool of this complexity and rich parameter space. It covers all presets, the hints mechanism and its benefits, conditional temporal behavior, and the returned payload. The output schema is available separately, so the description's return-value summary is sufficient. An agent can confidently decide whether to run this tool and how to configure it.

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 thoroughly: preset values are fully enumerated with levels and runtime, and hints are explained with a list of keys and their effect on downstream checks. source_id is not explicitly described but its purpose as the target source is self-evident from the name and sibling tools. All three parameters are made actionable.

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 specific verb and resource: "Run a preset bundle of checks." It clearly differentiates this aggregate EDA tool from the many individual check siblings (e.g., check_quality, check_bias) by emphasizing presets and the returned summary card, run_id, and artifact path. The purpose is unambiguous and well-scoped.

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 preset breakdown (quick, standard, deep, exhaustive) provides clear context for when to use each level, including runtime estimates and included checks. The hints section explains when to provide hints (to unlock leakage/bias checks and pre-fill follow-up calls). However, it does not explicitly state when to prefer this bundled tool over running individual check tools directly, so it lacks explicit exclusions/alternatives.

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