qlty_columnSummary

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

The description states that if persist=True, it 'materializes result as a volatile table and returns table name', implying a write side effect. However, annotations declare readOnlyHint=true and idempotentHint=true. The description contradicts these annotations by describing a potentially state-changing behavior. According to scoring rules, this contradiction results in a score of 1.

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 two paragraphs: first for purpose/usage, second for arguments. It is reasonably concise and front-loaded, though the argument list is redundant with the schema. No unnecessary sentences. Slightly verbose but acceptable.

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 omits what the summary statistics actually contain; it only says 'summary statistics for ALL columns' without specifying which statistics (mean, count, etc.). Since there is no output schema, the description should elaborate on the return format. Additionally, the contradiction with annotations creates confusion about the tool's side effects. For a tool with no output schema and a complex return, more detail is needed.

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% (all three parameters described in schema). The description lists the arguments but only restates information from the schema without adding new semantics. Baseline is 3, and the description does not exceed this.

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 clearly states 'Get summary statistics for ALL columns in a table in a single call' and distinguishes from the sibling tool qlty_univariateStatistics for single column stats. The verb 'Get' and resource 'summary statistics for all columns' are specific and unambiguous.

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?

Explicitly provides when to use: 'when the user asks for an overview, profile, or summary of every field in a table.' Also provides when not to use and alternative: 'For detailed statistics on a SINGLE specific column... use qlty_univariateStatistics instead.' This is excellent guidance.

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