find_similar_columns

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

Goes beyond the readOnlyHint annotation by detailing the composite score components (name token Jaccard, type, top-value overlap, cardinality, embedding cosine) and the union-find clustering with four classification categories. No contradiction with annotations.

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?

Four information-dense sentences with a front-loaded summary ('Multi-signal cross-dataset column consolidation'). Each sentence adds value without waste, though it is slightly longer than necessary.

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?

Given the tool's complexity and lack of output schema, the description covers the algorithm, use cases, and classification outputs. It doesn't specify the exact return structure (e.g., list of clusters with members), but the classification categories imply the output shape, making it mostly complete.

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 100%, so the schema already documents all four parameters. The description adds conceptual context (e.g., composite score floor) but doesn't materially improve parameter understanding beyond the schema.

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 a specific verb+resource: find similar columns across datasets. It explains the multi-signal fusion and cluster classification, distinguishing it from siblings like suggest_joins or describe_column.

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 lists use cases: find duplicate columns, surface naming drift, detect same conceptual column across multiple datasets. Mentions jcm's find_similar_symbols as a reference, but doesn't explicitly name alternatives or exclusion criteria.

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