Search Columns

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds behavioral value by specifying the output structure (table name, column name, and data type) and the pattern-matching semantics. It does not contradict annotations and provides context beyond the structured fields, though it omits details like pagination or performance considerations.

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 composed of three concise sentences: purpose with examples, return fields, and a follow-up recommendation. Every sentence serves a clear function without redundancy or filler. The most important information (what it does) is front-loaded, making it efficient for agent comprehension.

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 tool is a straightforward search function, and the description covers its core purpose, output, and a logical next step. An output schema exists, which likely documents the return structure in more detail, so the description does not need to repeat that. It adequately equips an agent to decide when to call this tool and what to expect, though it could mention result size limits or case sensitivity for perfect completeness.

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 provides 100% description coverage, including examples and usage notes for all three parameters (pattern, profile, magentoRoot). The tool description adds no parameter-specific meaning beyond what the schema supplies, so it meets the baseline of 3 without exceeding it.

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 finds tables containing columns matching a name pattern, specifies the return fields (table name, column name, data type), and provides concrete examples. It explicitly differentiates itself from describe_table by recommending it as the next step for full column details, making its purpose unambiguous and distinct among siblings.

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 description gives a clear directive to use describe_table next for full column details, which provides actionable follow-up guidance. It implies this tool is for coarse-grained column searches but does not explicitly state when not to use it or mention alternatives like find_order_by_increment_id, though the sibling context makes this less critical. The guidance is helpful but not exhaustive.

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