forget_memory

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

Annotations declare a non-read-only, non-destructive, non-idempotent mutation; the description goes further by disclosing the matching rule ('never meaning'), the ambiguity behavior (nothing removed, answer names the matches), and the calling convention (pass text exactly as recall returned it). This is real context beyond the annotations, though it never states whether the removal is reversible.

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?

Front-loaded with the action, then the calling convention, then the matching rule. Efficient overall, though the final 'when to use' sentence slightly restates the same idea twice.

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 an output schema present and annotations covering the safety profile, the description covers purpose, matching semantics, and trigger conditions adequately. The one gap is the local/global scope decision, which is a subtle routing choice left entirely to the 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?

Schema coverage is 50%: `text` is well documented in both places and the description usefully reinforces the exact-match rule, but `scope` (local vs global, an easily-misused default) is only covered by the schema and is never mentioned in the description.

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 ('Removes one statement') with the exact scope of the action: exactly one statement, matched by words. An agent can immediately distinguish it from recall_memory and record_memory without opening a 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?

Explicit when-to-use: 'Use it when a recalled statement is contradicted, and when a statement has simply stopped being true.' It even handles the edge case of matching more than one statement. It does not name a sibling as the alternative, but the recall-then-forget workflow is clearly implied.

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