brain_forget

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

With no annotations provided, the description fully carries the behavioral disclosure burden. It explains that matching memory notes move to a .trash folder, are recoverable by hand, and that chunks leave the index immediately while nothing is permanently destroyed. This gives the agent an accurate model of consequences and reversibility.

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 three tightly packed sentences: what it does, what happens behaviorally, and when to use it. Every sentence adds distinct value and the important purpose is front-loaded.

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 single-parameter, recoverable mutation tool with no output schema and no annotations, this description is complete. It covers semantics, behavior, recovery, and usage, leaving no significant gap an agent would need to resolve before invoking it.

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 the single parameter 'query' as matching filenames or content, and the description does not add new parameter-specific semantics beyond restating matching behavior. Since schema description coverage is 100%, a baseline of 3 is appropriate.

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The description opens with a specific verb and resource, 'Retract memories that are wrong or outdated,' which clearly identifies the tool's function. It also distinguishes itself from siblings like brain_remember and brain_search by focusing on removal/retraction rather than storage or retrieval.

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 'Usage' sentence explicitly states when to use the tool: when a remembered fact was superseded or was a mistake. It also names brain_search as the tool to consult first if uncertain, giving the agent a clear decision path.

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