Reject behavior correction

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

Annotations already identify this as destructive and idempotent, and the description's 'reject' is consistent with that. The description adds context about why a correction might be rejected but does not describe the mechanism or postcondition of rejection, such as whether the entry is removed or marked.

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?

One concise sentence with a helpful parenthetical and a direct instruction about where to find the ID. There is no redundant information or vague 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?

For a simple one-parameter action with an output schema present and safety annotations supplied, the description is sufficient to determine when and how to invoke it. It lacks only a formal statement of what rejection means, but annotations cover the destructive nature.

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 single id parameter has a description in the schema ('Correction ID (from memory_pending)'), and the tool description repeats this provenance. With full schema coverage, the description adds no additional parameter-level meaning, so the baseline of 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?

Clearly states the action ('reject') and the target ('a pending behavior correction'), with explicit rationale for when rejection is appropriate. The ID source is specified, and the name plus 'behavior correction' scope distinguishes it from sibling tools like correction_confirm and memory_reject.

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 actionable context by explaining that rejected corrections are those based on incorrect extraction or poisoned content and that the ID comes from memory_pending correction entries. It does not explicitly contrast it with correction_confirm, but the reject/confirm dichotomy is clear from the names and the stated rationale.

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