check_data_retention

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

With no annotations, the description fully carries transparency. It discloses file types scanned (.go, .yaml, .json, .toml), default response shape, pagination via cursor, and effects of filter parameters. It implies read-only scanning. There is no contradiction, and the behavior is well-explained.

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 detailed but not excessively verbose given the tool's complexity. It front-loads the purpose and then explains response shapes and pagination. Each sentence adds value, though some redundancy exists (e.g., mentioning response shapes multiple times). Overall well-structured.

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 covers all essential aspects: scanning scope, file types, response shapes, pagination, filtering, and PCI DSS mapping. Since an output schema exists, the description doesn't need to detail return fields. It provides sufficient context for an AI agent to correctly invoke the tool.

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?

All 8 parameters have detailed schema descriptions (100% coverage), so baseline is 3. The description adds value by explaining how parameters like min_severity and rule_filter change the response shape from summary to flat, and clarifies pagination behavior with cursor and limit. This context goes beyond schema descriptions.

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 scans for unsafe data retention patterns (CVV/PAN without TTL, missing TTL in configs, memory zeroing timing) in Go source and config files. It specifically names PCI DSS requirements, distinguishing it from sibling tools like check_secrets_in_configs or check_encryption.

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 provides guidance on when to use this tool (prefer for mixed queries) and how to use it (pagination, filtering, response shapes). It explains the default summary response and how parameters like min_severity affect the shape. However, it does not explicitly state when not to use it or compare to specific siblings.

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