record_decision

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

The description discloses that learning cannot change database activity, which is more specific than the annotation destructiveHint=false. It also mentions 'redacted' and 'scoped evidence', adding behavioral context beyond annotations. No contradiction.

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?

Two sentences, front-loaded with the core purpose, second sentence clarifies side effects. Efficient and free of unnecessary detail.

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?

Despite 24 parameters, the description captures the essence of the tool and its constraints. The output schema and parameter descriptions fill in operational details. However, it omits prerequisites like calling check_runtime_status for fingerprints, though those are noted in the schema.

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 description adds no parameter-specific details, but schema coverage is 63% with useful descriptions on parameters like skill and fingerprints. Baseline 3 is appropriate since the description doesn't need to compensate fully.

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: 'Record a redacted skill decision backed by scoped evidence.' This distinguishes it from sibling tools like review_decision and propose_lesson by focusing on persistence. The phrase 'redacted' and 'scoped evidence' adds useful constraints.

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 is implied but not explicit. The sentence 'Learning is advisory and cannot change database activity' provides safety context, suggesting when it's safe to call, but does not name alternatives or state when not to use this tool. No direct comparison to sibling tools like review_decision or propose_lesson.

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