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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds genuinely new context: the undo is surgical, 'preserving later work.' That preservation guarantee is the key behavioral fact an agent needs beyond the annotation flags. It still omits whether the undo itself is reversible or what permissions it requires.

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 sentences, both earning their place: the trigger condition first, then the scope and exclusivity rule. No filler or restated title.

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 mutation with no output schema and five parameters, it covers the trigger and scoping well but leaves the required document parameter, the operation_id retry semantics, and post-undo state undefined. Adequate but with clear gaps an agent would hit when actually calling it.

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 adds the mutual-exclusivity rule for act vs turn_id that the schema only implies, which is real value. But at 60% schema coverage, the required 'document' parameter has no description anywhere, and 'agent'/'operation_id' get no clarification in either place.

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+resource: taking back a change of yours in Rapier, scoped to exactly one act or one turn. This is distinguishable from the edit sibling since it implies reversal rather than modification, though the description never names edit directly.

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?

'Use this when the person wants a change of yours in Rapier taken back' is an explicit trigger condition, and 'act or turn_id, not both' guides parameter choice. It stops short of saying when-not to use it or pointing to a specific alternative tool for other reversal needs.

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