agent_forget

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new context beyond that: there is no recycle bin, deletion is permanent, what the success string looks like, and that an already-absent key yields a not-found error rather than a silent success.

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?

Three sentences, front-loaded with the destructive action and its scope, then the routing guidance, then the return contract. Every clause earns its place; no filler.

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?

With no output schema, the description usefully documents the return contract ('Forgot "KEY"' / not-found error), and for a one-parameter destructive tool the combination of annotations plus the permanent/no-recycle-bin note is fully sufficient.

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 100% for the single 'key' parameter, so the schema already carries the meaning. The description adds only 'from encrypted agent memory' as scope context, with no key-format or naming-convention guidance. Baseline 3 applies when the schema does the work.

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 and resource ('Permanently delete a single key from encrypted agent memory') and explicitly distinguishes itself from the two most confusable siblings, agent_remember and delete_secret. An agent can route correctly without opening any schema.

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?

Gives explicit when-to-use ('retract obsolete or misremembered context') and when-not-to-use, naming both alternatives with the condition that selects each (agent_remember for value updates, delete_secret for real credentials). Nothing is left to inference.

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