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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds the non-obvious behavioral trait that newer history is preserved, and that this is a 'Prepare' (staging) step rather than the authorized publish. That materially refines the destructive semantics the annotations alone would imply.

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, front-loaded with the action and its scope before the restriction and the publishing caveat. The jargon is dense but every clause carries information; little is wasted.

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 four required parameters and no output schema, the description covers the what and the when but leaves all parameter meaning unexplained and does not clarify the staged/preview result. Annotations carry the safety profile, which keeps this at a minimum-viable 3 rather than lower.

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 four required parameters (app_id, environment, checkpoint_id, expected_revision). The description names none of them and explains no semantics such as what expected_revision guards against or what checkpoint_id refers to, so it does not compensate for the schema gap.

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 ('Prepare Undo'), a resource (parent checkpoint), and a scope ('in Preview'), with the key qualifier 'preserving all newer history'. It implicitly contrasts with the redo sibling via the word 'Undo', but never names an alternative, so it stops short of a clean 5.

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 gives a usage restriction ('Closed stateless fixture or independently pinned static-export recipe only') and a routing hint ('publishing still uses the existing separately authorized deployment operation'). However the restriction is opaque jargon and no sibling (e.g. beon_prepare_app_checkpoint_restore, beon_prepare_app_redo) is named, so an agent must infer which case applies.

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