forget_memories

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

With no annotations provided, the description carries the behavioral burden and does so well: deletion is hard and irreversible ('matching rows are gone, not hidden') and an unfiltered call is rejected. It does not cover permission requirements or response behavior, but the destructive traits that matter most are disclosed.

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 with a front-loaded lead, an illustrative usage sentence, and a behavioral warning. There is no filler; the slight repetition of permanence reinforces the destructive nature rather than wasting space.

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 two-parameter tool with full schema coverage and an output schema, the description covers the key context: batch use, filter requirements, and hard deletion. The only minor gap is that the interaction between tag and age filters when both are supplied is not explicitly labeled as AND/OR, though the schema conditions imply both apply.

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%, so the baseline is 3. The description adds value by stating that at least one filter is required even though the schema marks neither property as required, and it supplies concrete usage examples for both parameters.

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 names a specific verb and resource ('Permanently delete memories') and the exact filtering dimensions ('by tag and/or age'). The phrase 'prune stale facts en masse' clarifies batch scope and distinguishes it from the singular sibling tool forget_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?

It gives a clear when-to-use instruction ('Use this to prune stale facts en masse') with concrete examples (scratch tag, older than 90 days). It also states the safety precondition that at least one filter is required, though it does not explicitly name alternatives or when-not conditions.

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