memory_forget

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

With no annotations supplied, the description carries the full burden and does so well for the destructive aspect: it discloses irreversibility ('Permanently'), the full blast radius across four storage layers, and the confirm=true safeguard. It stops short of covering permission requirements or what happens if the id does not resolve, which is why it is not a 5.

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 sentences, both front-loaded with the highest-value information: what is destroyed first, then the usage constraint. No filler, no repetition of the tool name, and the safety gate is placed at the end where it reads as a final check.

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?

An output schema exists, so return values need not be explained, and the description covers the two things an agent most needs for a destructive tool: scope of destruction and the confirm gate. Gaps remain around id formatting, not-found behavior, and whether related links are also removed, which are material for a permanent deletion.

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 does add real meaning for 'confirm' by asserting confirm=true is required, which is not obvious from the schema's default of false. However, it says nothing about the format or expected value of 'id' (the sole required parameter), so half the parameter surface remains unelaborated.

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 and resource — 'Permanently delete a memory and all its versions' — and enumerates the exact surfaces affected (files, git history, search index, embeddings). This clearly separates it from sibling tools like memory_correct or memory_history, which read or amend rather than destroy.

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?

Gives an explicit precondition: 'Only on the user's explicit request; requires confirm=true.' That tells the agent when this tool is appropriate and adds a hard gate before invocation. It does not name a specific alternative (e.g., memory_correct for fixing a wrong memory), which is the only thing keeping it from a 5.

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