purge_memory

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

No annotations are provided, so the description carries full burden. It discloses the destructive irreversible nature, the exact deletion scope, and the confirm_phrase requirement. However, it does not mention authorization needs or response format.

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 a few sentences long, each adding value. It is well-structured with a warning and guidelines, though slightly verbose. 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?

Given no output schema, no annotations, and only 2 parameters, the description is fairly complete. It covers purpose, usage, and parameter semantics. Missing information about return values or permissions, but still adequate for a simple tool.

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%, but the description adds critical meaning: it explains that confirm_phrase must exactly equal 'DELETE <uid>' and must come from the user's own message, and that uid identifies the memory. This partially compensates for the lack of schema descriptions.

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 clearly states the tool permanently deletes a memory along with its edit history and relations, using specific verbs and resources. It distinguishes itself from the sibling 'forget' tool by highlighting irreversibility.

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?

Explicitly advises using 'forget' instead unless permanent removal is requested, and gives a strict guardrail for the confirm_phrase parameter, preventing the agent from constructing the confirmation string itself.

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