forget

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

No annotations provided, but description discloses reversibility, audit logging of reason, and required confirmation protocol. Lacks details on potential errors or side effects.

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 efficient sentences pack purpose, effect, constraints, reason importance, and alternative tool – no redundancy.

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?

Covers all key aspects for a simple mutation: purpose, constraints, parameter context, sibling relations. Minor gap: no description of return value or error cases, but acceptable given lack of output 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?

Schema covers 100% parameter descriptions; description adds value by explaining reason's audit trail and visibility via audit(mode=archived).

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?

Description clearly states 'archive a memory' with specific effect (no longer surfaces in search, restorable) and distinguishes from sibling 'forget_all' and 'restore'.

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 when to call (after explicit user confirmation), when not to (implication/casual mention), and alternative tool (forget_all for multiple).

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