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

With no annotations, the description carries the full burden and does disclose real behavioral traits: it is a write/mutation that 'writes its files to the site', that a version saved with mode 'overwrite' left no checkpoint (so it may not be recoverable), and that it requires reading a contract doc first. It stops short of stating what is overwritten in the live site beyond the version's files, so not a full 5.

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?

Purpose and the disambiguation from submit-version are front-loaded, and every clause carries information. The dense em-dash and parenthetical packaging makes it slightly harder to parse than it needs to be, but there is 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 2-param write tool with an output schema (so return values need not be explained), the description covers prerequisites, the alternative sibling, and a key limitation. The 'overwrite leaves no checkpoint' caveat is useful but terse and could be clearer about recoverability.

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 100%, so both parameters are already fully documented (blockId from list-blocks, versionId uuid from list-versions). The description references list-versions but adds no syntax or format semantics beyond what the schema provides. Baseline 3 is appropriate here.

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 ('Make an EARLIER version the live one again and write its files to the site') and explicitly contrasts itself with the sibling submit-version ('submit-version already deploys'). An agent can distinguish it from submit-version and list-versions without opening any 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?

Names the condition for use ('only to undo a version that turned out wrong'), the alternative that already covers the normal path (submit-version), the prerequisite doc to read before the first call (get-skill-doc {id:'block-contract'}), and where the versionId comes from. Nothing is left to inference.

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