Turn learning on or off

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

Goes well beyond the lone idempotentHint annotation: discloses the default ('on by default'), the exact scope of what is recorded (accepts, rejects, cuts, clip edits), the fact that disabling is non-destructive, and the retention rule until forget_decisions. The return shape is also given. Missing only auth/permission notes, which keeps it from a 5.

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?

Three short clauses, front-loaded with the state semantics before the retention caveat and the return shape. Slightly fragmentary opening, but no sentence is wasted.

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?

For a one-boolean, idempotent settings toggle this covers everything an agent needs: default state, effect of each value, data-retention consequence, the relevant alternative tool, and the response shape. Nothing material is left to guess.

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 100% and the single boolean is already documented, so the baseline is 3; the description earns a step up by enumerating the decision types that get recorded and clarifying that 'off' merely stops new recording rather than deleting anything.

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?

Names the resource (Reelsaw decision recording / Learning setting) and the effect of both states, so an agent can tell it apart from the nearby forget_decisions and list_decisions siblings. It is phrased as a fragment ('Whether Reelsaw records...') rather than a verb+object statement, which costs a bit of crispness but not comprehension.

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 states the consequence of each state ('Off stops recording') and points to the sibling to use for actually removing data ('stays until forget_decisions'), which is a real routing decision. It does not spell out an explicit when-to-use trigger, but the toggle semantics make the selection obvious.

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