undo_apply

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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, but the description adds real value beyond them: the inverse executes through its own governed tool with its own risk tier recorded on the audit row, dry_run previews without executing, and a token is single-use (consistent with idempotentHint=false). It does not describe error behavior if the token is already consumed, but the added context is substantial.

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?

Front-loads the write/risk tag and the core action, then adds only the constraints that matter (single-use token, dry_run preview). The Args block repeats schema field names but is justified given 0% schema description coverage; wording is tight with no 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 mutation tool with no output schema, it covers the essentials: risk tagging, audit behavior of the inverse, dry-run path, and single-use tokens. Missing is any guidance on failure modes (expired/consumed token) or what a successful result reports, but the core operational picture is 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 description coverage is 0%, so the description carries the parameter burden, and it documents all three: undo_id (source: undo_list or _undo_id from a write result), dry_run (preview semantics), and target (passed through when the inverse accepts one). The target explanation is slightly soft about what values are valid, preventing a 5.

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 ('Apply a recorded undo by dispatching its inverse tool') and the mechanism, which cleanly separates it from the sibling undo_list that only enumerates undo tokens. An agent can tell exactly what this tool does without opening the schema.

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?

Explains where undo_id comes from ('from undo_list (or an _undo_id in a write result)') and when to use dry_run for a preview, which is clear contextual guidance. It stops short of stating when *not* to apply an undo (e.g. token already consumed, which is only implied by 'A token can only be applied once').

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