memory_key_facts_forgetSoft-delete a stored key fact by its UUID, removing it from active recall while keeping the record recoverable.
Soft-delete a stored key fact by its ID.
| Name | Required | Description | Default |
|---|---|---|---|
| fact_id | Yes | UUID of the fact to forget |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, but the description adds genuinely new information beyond them: the deletion is a *soft* delete, so the fact is retained rather than purged. That nuance materially changes how an agent should treat the operation. It still omits who may perform it and how a soft-deleted fact behaves in subsequent retrieve/stats calls.
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?
One sentence, zero filler, with the verb and target front-loaded. Nothing to trim.
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 mutation with annotations covering the safety profile and no output schema, the description is close to adequate. However, it leaves the post-condition of a soft delete unexplained (does the fact still appear in retrieve/stats?) and gives no recovery guidance, which an agent mutating memory state would benefit from.
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 single fact_id parameter is fully documented as a UUID in the schema, so the description's 'by its ID' adds no meaning. Baseline 3 applies when the schema carries the parameter burden.
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 (soft-delete), resource (stored key fact), and lookup key (by its ID), which clearly separates it from siblings like memory_key_facts_remember, memory_key_facts_update, and memory_key_facts_retrieve. It does not explicitly name those siblings, but the purpose is unambiguous without opening the schema.
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?
No guidance on when to forget versus update a fact, no prerequisites, and no mention of whether an undo/restore path exists. Usage must be inferred from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.