forget_memory

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description reinforces this with 'permanently delete,' making irreversibility explicit. It also adds useful behavioral constraints beyond annotations: the user must have stated the memory was recorded in error, the memory must belong to the current workspace, and using supersedesId preserves history.

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?

Three short, purposeful sentences with no filler. The core action is front-loaded, followed by a clear usage condition and a helpful alternative recommendation. Every sentence earns its place.

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, single-required-parameter tool, the description covers the critical aspects: what is deleted, when deletion is allowed, the workspace restriction, and the preferable alternative for fact changes. The annotations and output schema cover safety and return semantics, so nothing essential 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?

The schema already documents scope and taskId, but the required id parameter has no description beyond type and length constraints. The description does not clarify what id represents or how the agent should obtain it, though the tool name and context make this inferable. At 67% schema coverage, the description could have compensated for the undocumented id but does not.

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 description opens with 'Permanently delete a memory,' naming a specific verb and resource, and clarifies the narrow condition under which deletion is appropriate (user says it was recorded in error). It also distinguishes itself from save_memory by explicitly contrasting deletion with supersede-based updates.

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 description gives explicit when-to-use guidance: only when the user says the memory was recorded in error and the memory belongs to the current workspace. It also states when not to use it, directing agents to save_memory with supersedesId when a fact changed, so the alternative routing is unambiguous.

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