undo_apply

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

Annotations are None, so the description carries the burden. It discloses the write risk tier '[WRITE][risk=medium]', explains the inverse runs through its own governed tool with its own audit/labelling, and states the single-use constraint. However, it doesn't detail what happens on failure, return payload shape, or whether state changes are immediately visible. The 'governed tool' comment adds context beyond annotations but could go further.

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?

Efficient and well-structured: a one-sentence purpose line, compact behavioral facts (audited, single-use, dry-run), a risk marker, then a brief Args section mapping to each parameter. Every sentence earns its place with zero waste.

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 write/dispatch tool with 3 params (1 required), no output schema, and no annotations, the description covers the key aspects: purpose, risk tier, dry-run preview, single-use constraint, and parameter provenance. Slightly incomplete on failure behavior and what the inverse call's success/failure looks like, but reasonably complete for guiding a competent agent.

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. It explains undo_id as coming from undo_list or an _undo_id in a write result, dry_run as preview-without-executing, and target as pass-through. This adds meaningful semantics beyond the bare schema, though target's condition ('when it accepts a target') is somewhat vague.

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 what it does: 'Apply a recorded undo by dispatching its inverse tool.' The verb 'Apply' + resource 'recorded undo' is specific. Distinguishes from siblings by the mechanism (dispatching inverse tool) and the write-context trait ('[WRITE]').

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?

Provides clear usage context: dry_run=True to preview, token can only be applied once, and target pass-through semantics. Doesn't explicitly name alternatives or when-not-to-use, but the 'token can only be applied once' and dry_run guidance give practical usage direction.

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