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

Annotations already declare destructive=true, idempotent=false, and openWorld=true, so safety is partly covered. The description adds real behavioral context beyond them: ambiguity is never auto-resolved ("Ambiguous branches are never guessed") and redo does not discard newer history ("no newer history is erased"), which materially shapes agent expectations. It omits whether a follow-up commit/confirmation step is required.

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?

Three short, front-loaded sentences with no filler; the operation and its scope restriction are stated first. The dense, undefined jargon ("Prepare Redo", "pinned static-export recipe") costs some readability without adding length.

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, non-idempotent mutation with five required parameters at 0% schema coverage and no output schema, the description is under-specified. It never explains the prepare/commit lifecycle (what a successful "prepare" produces or whether a second call is needed) nor the role of expected_revision, which an agent must understand to call this safely.

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% across five required parameters, so the description carries the full burden and fails to explain any of them. app_id, environment, checkpoint_id, expected_revision (an optimistic-concurrency guard), and current_checkpoint_id are never mentioned or defined, even though the concurrency parameters are exactly where an agent would err.

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 names a specific operation ("Prepare Redo") and the target resource ("an explicitly selected direct child version in Preview"), so the agent can distinguish it from a generic restore. It does not explicitly contrast with the obvious sibling beon_prepare_app_undo, leaving the redo-vs-undo distinction to inference.

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 states an applicability restriction ("Closed stateless fixture or independently pinned static-export recipe only") which is a genuine when-to-use condition. However, it names no alternative tool and gives no explicit when-not-to-use guidance relative to beon_prepare_app_undo or beon_prepare_app_checkpoint_restore.

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