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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world behavior, and the description adds real context on top: it captures an immutable snapshot of the exact draft state, produces no publication, and deliberately refuses a boolean consent parameter. It does not say what persisted record or handle is produced, or what happens if the destination revision no longer matches, which keeps it below 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?

Two dense sentences with no filler; the snapshot scope is front-loaded and the safety constraint ('never publishes') follows immediately. The enumerated noun list is slightly heavy but each item conveys a real capture dimension.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, for a four-parameter, all-required preparation tool, the description leaves gaps around the idempotency key, workspace scoping, and what the agent should do when the expected revision is stale.

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%, so the description must carry the burden. It adds conceptual meaning for two of four parameters (draft_id via 'saved draft', expected_revision via 'destination revisions'), but request_key and workspace_id are never mentioned, and the idempotency role of request_key is left for the agent to infer from annotations alone.

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 action ('Snapshot') and its object (the saved draft, assets, destination revisions, visibility/disclosures), which is far more precise than the bare title 'Prepare social publication'. It implicitly separates itself from publishing tools by stating preparation 'never publishes', though it never names publish_social_draft, prepare_social_schedule, or review_social_draft explicitly.

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?

Usage context is clear: this is the step that precedes 'authenticated creator approval', and the exclusion 'Preparation never publishes' tells the agent not to reach for it as a publish action. It stops short of a 5 because no sibling tool is named as the alternative for the publish or schedule step.

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