memory_forget

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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description reinforces this by emphasizing 'Permanently' and enumerating the artifacts destroyed, which adds useful consequence context beyond the boolean. It doesn't cover auth or reversibility guarantees, hence a 4.

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 destructive nature and the usage gate; nothing wasted.

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?

Output schema exists, so return values needn't be explained, and the safety profile is covered by annotations. The main missing piece is what the id refers to and how to find it before calling a destructive operation.

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?

One parameter 'id' with 0% schema description coverage, so the description must compensate—and it doesn't mention what the id is (file id, graph id, memory id?) or how to obtain it. This is a real gap for identifying the target object.

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?

'Permanently delete a memory' states a specific verb and resource, and the parenthetical enumerates exactly what gets removed (file, graph, archived copy, index), distinguishing it from read siblings like memory_recall and memory_get.

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?

The qualifier 'Only when the user asks to forget something' gives a clear gate on when to use it, effectively signaling when-not. It doesn't point to a specific alternative, but the constraint is actionable.

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