purge_forgotten

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It states the operation is permanent and irreversible, explains that it is never automatic, and reassures that it only touches forgotten memories. It also includes the default retention period as a safety behavior, which is valuable context for an agent deciding to invoke a destructive operation.

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 description is front-loaded with the primary action and then uses compact paragraphs for contrast, safety guarantees, and parameter semantics. Each sentence earns its place: even the 'dead row' background explains why the tool exists and supports the usage decision. It is detailed without being bloated.

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 one-parameter tool with an output schema present, the description is complete. It covers what the tool does, when to use it, how the parameter behaves, the safety default, and the boundary conditions. No essential information for invoking it correctly 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 description coverage is 0%, so the description is the only source of parameter meaning. It fully explains `older_than_days`: only forgotten memories at least that many days old are purged, the default preserves a month of recovery, and passing 0 purges all forgotten memories regardless of age. This is exactly the semantic detail the schema lacks.

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 a specific verb and resource: 'Permanently delete memories that were forgotten a while ago.' It clearly distinguishes itself from `forget`, which it explicitly identifies as a soft delete, and marks this tool as the irreversible counterpart. An agent can tell exactly what this tool does and how it differs from siblings.

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 explicitly contrasts with `forget`, explaining that `forget` keeps the row for recovery while this tool is the 'deliberate, irreversible half.' It also clarifies when it is appropriate: only for memories already marked forgotten, never active ones, and never automatically. This gives an agent clear guidance on when to choose this tool over alternatives.

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