undo_backfill

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

With no annotations, the description carries full responsibility. It discloses return shape ({restored, refused}), error behavior (raises when nothing restored), logging (both retirement and undo stay in message_history), and the reason length limit. It does not mention idempotency or partial-failure details, but it is otherwise transparent.

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?

The description is compact, front-loaded with purpose, and every sentence adds essential detail: constraints, permissions, return value, logging, and reason limit. No filler or redundancy.

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?

Despite lacking explicit parameter explanations, the description covers purpose, usage restrictions, permissions, return format, error behavior, logging, and constraints. For a tool with a simple two-parameter schema and an output schema, this is nearly complete.

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 0%, so the description must compensate for both parameters. It only addresses 'reason' (length limit), leaving 'ids' as implicit – an agent must infer that ids refer to the records to restore. This is insufficient for reliable parameter understanding.

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 states a specific verb and resource: 'Undo a cleanup: put back records that backfill_superseded retired.' It explicitly distinguishes from the related tool by clarifying what it cannot undo (proposal retired by a vote or new pin version), making its purpose unambiguous and separating it from siblings.

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 provides explicit when-to-use conditions: only retirements from a cleanup pass can be undone, and only the role that applied the pass or the owner of the key may use it. It also states exclusions (vote-based or pin-version retirements), giving clear guidance on when not to use it.

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