dakera_batch_forget

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

With no annotations the description must carry the safety profile, and it does by flagging the operation as 'Permanent' and pairing it with a non-destructive alternative. It does not disclose what the call returns (e.g., deletion count) or how multiple filters combine, so the destructive disclosure is strong but not exhaustive.

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 tightly packed sentences: the operation, its filter surface and its prerequisite come first, followed by the safety note and the alternative. No filler and no redundancy with the schema.

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, no-annotation, no-output-schema tool, the description covers permanence and filter scope but omits return behavior and whether the filters AND together versus OR. Adequate to call correctly, but a few gaps remain for a tool whose effects are irreversible.

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 description enumerates the filter families (tags, importance range, time window, type, session), which maps onto most of the eight parameters, and adds a cross-parameter rule ('at least one is required') that the schema itself does not encode. It stops short of syntax details for the timestamp/importance bounds that the schema partly covers at 63%.

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 ('Bulk-delete memories') plus the qualifying dimension (matching filters) in a single clause. It is clearly distinguishable from the single-record dakera_forget and from dakera_memory_importance, which it names.

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 the selection constraint ('matching filters ... at least one is required') and routes the agent to the correct alternative for the non-destructive case ('to demote instead, use dakera_memory_importance'). It lacks guidance on when to prefer this over per-record deletion, but the context is otherwise clear.

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