memory.forget

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

With no annotations, the description carries the full burden. It discloses that removal cascades to tags, links, and embeddings, which is valuable behavioral context. However, it omits critical details: whether removal is permanent or reversible, required permissions, and what happens if the pattern doesn't exist. The cascade hint is useful but insufficient for 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?

A single, front-loaded sentence that efficiently conveys the core action and its cascading effect. No wasted words; the parenthetical adds essential context without bloat.

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 operation with no annotations, no output schema, and 0% schema coverage, the description should do more. It lacks information on reversibility, error conditions, and permissions. The cascade hint is helpful but the definition remains incomplete for an agent to invoke this tool safely and confidently.

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?

With one parameter and 0% schema description coverage, the baseline is 4. The description doesn't add meaning to 'patternId' beyond what's implied by the tool's purpose, but with only one required parameter of type integer, the schema is self-explanatory enough that no additional parameter guidance is strictly necessary.

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?

States a specific verb ('Remove') and resource ('a pattern from memory'), and the parenthetical clarifies the blast radius (cascades to tags, links, embeddings). This clearly distinguishes it from siblings like memory.store, memory.recall, and memory.evolve, which operate on different aspects of memory.

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 provides no guidance on when to use this tool versus alternatives (e.g., memory.evolve might also modify patterns). It does not state prerequisites or conditions for use, leaving the agent to infer usage from the name alone.

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