Find sensitive columns

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds value by explaining the heuristic nature (no row sampling, no value introspection), listing categories, and detailing confidence levels (high/medium/low). This provides behavioral context beyond 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?

The description is concise and front-loaded with the core verb and resource, followed by key details (categories, confidence, caveat). Every sentence adds value with no redundancy, using proper punctuation and structure.

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 fully explains the tool's behavior, output structure (findings list with fields and summary counts), and caveats. Given the output schema exists (as per context signals), the description need not repeat return types, and it complements the schema with clear purpose and usage context.

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 50%: the 'database' parameter has a description in the schema, but 'schema' does not. The description does not elaborate on either parameter beyond what the schema provides. The inherent context of the tool's purpose indirectly clarifies the 'schema' parameter, but the description adds no explicit parameter guidance, so baseline of 3 is appropriate.

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 explicitly states the tool flags columns that look like sensitive data (passwords, tokens, PII, etc.), specifying it is a pure heuristic without row sampling. This clearly distinguishes it from sibling tools which are mostly analysis or audit operations, providing a unique purpose.

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 advises treating the output as a signal, not a verdict, and gives a concrete example (email_template_id). It implies usage for a first pass review, but does not explicitly state when not to use or mention alternatives. This is clear guidance but lacks explicit exclusions.

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