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

The annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, and the description adds real substance beyond that: edits replace prior draft values entirely, arrays overwrite the whole list, and only the draft is mutated while the live store is untouched. This concretely explains the nature of the destruction, which annotations alone cannot. It does not mention required permissions or whether a follow-up publish step is needed, so it falls short of a 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?

Three tight sentences, each carrying a distinct constraint: what it mutates, what it does not mutate, and the overwrite semantics. The key safety warning ('check the draft first') is embedded exactly where it is needed, 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 destructive mutation with a nested payload object and no output schema, the description covers the essentials: scope of mutation, replacement semantics, and partiality of the payload. The remaining gap is the undocumented shape of `changes` and the absence of guidance on what happens afterward (e.g., that publishing is a separate step).

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 only 33% — `store` is documented in the schema while `draft_id` and the nested `changes` object are bare. The description compensates well for the riskiest parameter by stating that `changes` is partial and uses replace-whole-list semantics for arrays, but it never enumerates what fields `changes` accepts, and `draft_id` semantics are left entirely to the name.

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 ('Change a draft or a set of unpublished changes') and the title reinforces it with the key constraint ('store not changed'). It does not explicitly differentiate itself from close siblings such as stage_changes, create_draft, or preview_draft, so an agent must still infer the boundary.

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?

'before it is published' plus 'check the draft first' implies the usage context: inspect the draft, then edit it, then publish. However, there is no explicit statement of when to use this versus stage_changes or create_draft, and no exclusions or prerequisites (e.g., required permission scope) are given.

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