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

Annotations already declare destructiveHint=true and idempotentHint=true, covering the safety profile. The description adds context about clearing sensitive data and that memories were previously saved by the agent, but doesn't disclose additional behaviors like return values or error handling.

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?

Two sentences, front-loaded with the verb and object, no filler. The pairing note and usage conditions are concise and relevant.

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 destructive operation with idempotent annotation, the description covers purpose, trigger conditions, and relationship to related tools. It is complete for the tool's complexity even without an output schema.

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 input schema covers 100% of the parameter with a description ('Memory key to delete'). The tool description simply says 'by key,' which adds no new semantic detail beyond what the schema provides, so baseline 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 clearly states 'Delete a previously stored memory by key,' identifying the specific action and resource. It distinguishes itself from sibling tools like remember and recall by naming them as companions, implying its complementary role as the deletion operation.

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?

It gives explicit when-to-use guidance: stale context, completed tasks, or clearing sensitive data. It also mentions pairing with remember and recall, but does not explicitly state when not to use it or name alternatives beyond these collaborators.

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