Forget decisions

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description adds important context: deletions cannot be undone, affect learning behavior, and return { forgotten, message }.

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 short and front-loads the destructive operation and its learning consequence. The parenthetical phrase 'projectId, live or already deleted forever' is slightly awkward but overall the sentence is efficient.

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-parameter destructive tool with no output schema, it covers the essential scope, irreversibility, learning effect, and return shape. It could be more complete by relating explicitly to set_learning or non-destructive decision-log tools.

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 description coverage is 100%, and the one optional projectId is already documented. The description reinforces that omitting projectId deletes everything, but adds little syntax or format detail beyond the schema.

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?

States a specific verb and resource: delete entries from the decision log, with the consequence that Reelsaw stops learning from them. This clearly distinguishes it from sibling read/export tools like list_decisions and export_decisions.

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?

Explains project scoping well: projectId limits deletion to one project, omission deletes all. However, it gives no explicit guidance on when to use this versus related tools such as set_learning, list_decisions, or export_decisions.

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