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

Annotations only declare destructive=true and idempotent=false; the description adds what is actually destroyed ('discards later edits from that active view'), what survives ('prior revisions remain available'), the failure mode (stale currentHeadRevisionId rejects with REVISION_CONFLICT), the policy gate (interactive approval), and the async nature (returns a restore job, terminal state via job_wait/job_get).

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?

Four dense sentences, front-loaded with the effect and destruction, then prerequisites, then failure/policy behavior, then return semantics. No filler and nothing duplicates the title.

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 async mutation with no output schema, the description covers effect, data loss, siblings to consult first, conflict handling, approval policy, and how to obtain the terminal result. Nothing an agent needs to invoke it safely 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 real meaning for currentHeadRevisionId by explaining that a stale value triggers REVISION_CONFLICT, giving the optimistic-concurrency parameter a purpose beyond its schema text.

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 ('Replace the current scene contents with a historical revision, creating a new head revision') and immediately clarifies the resulting state. An agent can distinguish it from sibling revision_diff (review) and scene_apply without opening a 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?

Explicitly routes the agent to revision_diff to review changes first and project_get to read the exact current head, which is real when-to-use guidance. It does not, however, contrast with other mutation siblings (scene_apply, preset_apply) that might also alter scene contents.

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