profile

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

The description discloses output characteristics (per-column stats, ~1-3KB per column) and performance (single DuckDB SUMMARIZE pass, fast on millions of rows), which adds behavioral context. However, with no annotations provided, it does not explicitly state that the tool is read-only or whether it has side effects, leaving some transparency gaps.

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 concise, front-loaded with the core purpose, and uses bullet points for clarity. Every sentence adds value—purpose, statistics details, performance, and output scaling—with no redundancy.

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 existence of an output schema means return values are already documented. The description covers output content and performance, but misses parameter semantics and explicit usage guidance. For a simple 2-parameter tool, this is moderately complete but has clear gaps.

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 carries the full burden of explaining parameters. It fails to explain what 'source_id' refers to or how the optional 'columns' parameter behaves (e.g., omitting means all columns). Only the output behavior is described, not the inputs.

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 the tool's purpose with a specific verb ('profile') and resource ('per-column'), and enumerates the exact outputs (type, null%, cardinality, stats). It distinguishes itself from siblings like describe_source or check_distributions by focusing on column-level profiling with a DuckDB SUMMARIZE approach.

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?

Usage context is implied through the performance claim ('fast on millions of rows') and the detail about output size, suggesting it's for quick column profiling. However, there is no explicit statement about when to choose this over alternatives like describe_source or check_distributions, nor any exclusions.

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