get_columns_used

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

readOnlyHint=true already tells the agent this is a safe read, and an output schema exists so return values need no explanation. The description does add the notion that the result is a frequency map (counts, not a plain list), which is useful behavioral context, but says nothing about auth needs, scope limits, or cost.

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?

One tight sentence with no filler and the key concept front-loaded. It is efficient rather than padded, though it is arguably too terse for a tool sitting among many column/field-related siblings.

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?

Low-complexity read-only tool with one required parameter and an output schema, so most structure is already covered. What is missing is any routing context among the ~60 siblings or note on scope (single analysis vs. all visuals), which leaves a gap for correct selection.

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 coverage is 100% with a single documented analysis_id parameter, so the schema carries the burden. The description adds no extra meaning about the parameter, making the baseline 3 correct.

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 names a specific verb ('Get') and a specific resource with scope ('frequency map of columns used across an analysis'), so an agent can tell it apart from list_calculated_fields or get_parameters. It stops short of explicitly naming which sibling it competes with, which keeps it out of the top band.

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?

There is no statement of when to use this tool, when not to, or which alternative (e.g. list_calculated_fields, get_visual_definition) covers a related question. Usage is only implied by the phrase 'columns used'.

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