Retract a node and all connected edges from current memory views while preserving history for past reads; reads at NOW omit it.
Bi-temporal forget — retract a node and every edge connected to it. Historical reads still see it; reads at NOW skip.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Node name (also accepts a UUIDv7 id where the verb supports polymorphic resolution). | |
| initiative | No |
Changes observed during successful MCP inspections.
v0.7.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the cascade (node plus every connected edge), the bi-temporal semantics (historical reads still see it, reads at NOW skip), implying a soft/non-physical retraction. It omits auth/permission requirements, reversibility, and effect on the edges' other endpoints.
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?
Two tight sentences, front-loaded with the action and then the temporal behavior. Every clause earns its place with no filler.
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 destructive mutation tool with no annotations and no output schema, the description covers the most decision-relevant facts (cascade scope, temporal visibility). It could say more about reversibility and permissions, but nothing essential for a correct call is missing.
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 50% — 'name' is documented but 'initiative' has no description in either schema or text. The description adds no parameter-level detail (e.g., UUIDv7 acceptance or initiative scoping), so it does not compensate for the coverage gap.
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 ('retract') and resource ('a node and every edge connected to it'), plus a distinctive bi-temporal qualifier. It's clear what the tool does, but it doesn't explicitly differentiate itself from near-siblings like delete_initiative or supersede.
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 when-to-use guidance, no prerequisites, and no routing to alternatives. The description never says when to choose 'forget' over 'supersede', 'delete_initiative', or 'unlink', leaving selection to inference from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.