Scene Checkpoint

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

Annotations only declare readOnly/openWorld/idempotent/destructive flags; the description goes well beyond them, disclosing that checkpoints carry no undo history, that same-name saves are rejected unless overwrite=True, that the old file is preserved via rename, that references are flattened, and even naming the return fields (original_file_status, scene_rebound_to).

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?

Well front-loaded: the core action leads, then naming/overwrite rules, then honest bounds. Dense but each sentence carries information; the parenthetical 'Honest bounds:' framing is slightly editorial but useful rather than wasteful.

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?

Covers the full picture for a mutation-style tool: scope, file placement, failure modes (same-name rejection), preconditions (untitled scenes), and the limitations an agent needs (no undo history, flattened references, one scene file per session). Even though an output schema exists, the returned status fields are described usefully.

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 already 100%, so the baseline is 3, but the description adds real meaning beyond the schema by explaining the untitled-scene requirement for `name` and the preserve-via-rename semantics of `overwrite`. The session_key parameter remains unexplained in the description.

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+resource ('Save a real scene snapshot (exportAll of in-memory state)') and immediately distinguishes it from the sibling scene_snapshot by noting that one is for rebuilding context after rollback. Also differentiates from scene_viewport_snapshot by specifying a self-contained .ma written to checkpoints/.

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?

Explicit conditions are given: an explicit name is required on untitled scenes, overwrite=True is needed to replace an existing checkpoint, and scene_snapshot should be used after scene_rollback. Both when-to-use and when-to-use-the-alternative are covered.

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