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

Annotations only say non-readOnly, non-destructive, closed-world; the description goes well beyond them by naming the required key scope (deploy:write), stating explicitly that nothing is published and that history is preserved by creating a new version, and documenting the exact failure modes (409 draft_version_conflict with recovery, 404 draft_version_not_found). That is exactly the mutation-safety context an agent needs.

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-loaded with the core behavior first, then constraints, then errors, then next steps — a good information hierarchy. The trailing [When to use] block is generic boilerplate that is long relative to the tool-specific content, which costs some density.

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?

With no output schema, the description still covers what the call produces (a new draft version), what it does not do (nothing published), error semantics, and the mandatory follow-on steps. Nothing material for correct invocation is missing.

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 100%, so the baseline is 3, but the description adds constraints the schema cannot express: 'exactly one of the two' mutual exclusion between from_version and from_deploy, the 'last 20' bound on draft versions, and what expected_draft_version mismatch produces. This meaningfully reduces malformed calls.

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 ('a new draft version that copies an earlier draft version or a published version'), and immediately disambiguates the two source modes (from_version vs from_deploy). An agent can tell this apart from publish_draft, preview_draft and get_draft 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?

Gives concrete when-to-use conditions ('start editing what is live'), names the required inputs (get_draft's versions, list_versions) and the follow-up workflow (preview_draft then publish_draft). It never mentions the sibling 'rollback', which is the most plausible confusion for undoing a version, so the alternative-space is not fully closed.

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