forget

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

With no annotations, the description carries the full disclosure burden, and it delivers: content is tombstoned rather than destroyed, visibility disappears from recall() and list_anchors(), the reason is persisted, and a required predecessor (unpin) is named. This goes well beyond a simple mutation warning.

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?

Four short sentences, each carrying distinct information: purpose, retention semantics, reason requirement, and unpin prerequisite. The most important constraints are front-loaded in the second sentence rather than buried.

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 two-parameter mutation with no output schema, the description covers the core behavioral contract and prerequisite. It omits edge-case behavior (unknown memory_id, whether tombstone is restorable), but those gaps are minor given the strong core disclosure.

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 0%, so the description must compensate. It adds real meaning to reason (required/logged/accountable), but memory_id is only indirectly implied as the identifier of the memory to forget; no guidance is given on where it comes from or its format.

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 opening sentence names a concrete verb and resource ('Deliberately forget a memory') and immediately distinguishes the operation from a hard delete by describing tombstone retention. The effect on recall() and list_anchors() makes it unambiguous which behavior is being invoked.

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?

States a clear precondition (anchored memories must be unpin()-ed first) and clarifies that reason is mandatory and auditable. It does not explicitly contrast against sibling tools like restore or remember, but the 'not a hard delete' line provides a useful exclusion.

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