dashboard.get_dashboard_columns

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

Even though readOnlyHint is already annotated, the description adds valuable behavioral detail: it resolves the dashboard by title, exports full metadata, extracts column references from both filters and widgets, and deduplicates by table and column. It also discloses the exact output fields, which is especially useful given the absence of an output schema.

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 compact and front-loads the main purpose before diving into implementation details. The Returns section is clearly structured and avoids filler. A small amount of internal implementation detail could have been trimmed, but it remains useful for transparency.

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 single-parameter read-only tool, the description covers the operation, the return type, the fields included, the deduplication behavior, and the meaning of an empty list. It does not describe error behavior when a dashboard is not found, and the final 'empty list means …' sentence is cut off, leaving a minor gap.

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 input schema already describes dashboard_name as 'Title of the dashboard to retrieve columns from,' so coverage is high. The description adds extra meaning by explaining that the name is used to resolve the dashboard through get_dashboard_by_name, reinforcing that it is a human-readable title rather than an ID.

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+resource pair: 'Retrieve columns referenced by a dashboard, including widget and filter columns.' It also clarifies the tool resolves by title via get_dashboard_by_name, which distinguishes it from sibling tools like dashboard_get_dashboard_by_id.

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 intended use is implied through the phrase 'Retrieve columns referenced by a dashboard,' but there is no explicit statement of when to use this tool versus alternatives such as dashboard_get_dashboard_by_id or dashboard_find_widgets_by_type. The guidance is inferred rather than stated.

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