forget

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

The description discloses that despite the name 'forget', this tool is not destructive by itself and that deletion is deferred until action_commit confirms. It adds meaningful policy context about strong-confirm and unattended MCP clients, which is especially valuable given destructiveHint=false could otherwise be confusing.

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?

The first sentence is clear and front-loaded with the core behavior, and the second provides important policy context. The phrasing is a bit verbose and relies on unexplained 'Decision 8' jargon, but every sentence contributes meaningful information.

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?

The description explains the critical two-phase behavior and client safety constraint, but it omits details about what the preview response looks like, what happens to pending deletions before commit, and how the reason parameter is used. Since there is no output schema, additional behavioral detail would improve completeness.

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 0%, and the description does not explain the meaning or usage of memory_id or reason. The tool's purpose implies memory_id identifies the memory, but reason is left entirely unexplained, so the description does not compensate for the missing parameter documentation.

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 states a specific verb ('Preview deleting') and resource ('one memory'), and immediately clarifies the key limitation that nothing is deleted until action_commit confirms it. This distinguishes the tool from action_commit and makes its role in the deletion workflow clear.

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 explains the two-phase workflow and explicitly warns that an MCP client cannot delete in a single call because deleting data is classified as strong-confirm. It does not enumerate alternatives, but it names action_commit as the confirming step, giving enough context for when to use this tool.

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