Scene Checkpoint List

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is low. The description adds genuinely new behavioral context: results vary by scene type, with untitled scenes resolving to workspace ad-hoc snapshots and an adhoc flag per entry. It stops short of describing entry shape or ordering, but this is solid added value over the structured fields.

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 short sentences with no filler, and the core action is front-loaded before the source-dependent detail. The line-wrapped second sentence is slightly awkward but not 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?

With an output schema present, return values need not be explained, and the annotations carry the safety profile. The description covers the one non-obvious behavior (scene-type-dependent sources) and is adequate for this low-complexity, single-optional-parameter tool.

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 100% for the single optional session_key parameter, so the schema does the documentation work and baseline 3 applies. The description adds no extra meaning about session_key or whether it is needed for the lookup.

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: 'List all saved checkpoints for the current scene state.' It further distinguishes two data sources (saved scene <scene_dir>/checkpoints vs. untitled workspace ad-hoc snapshots), but never names the sibling tools it is *not* (e.g. scene_checkpoint for creating, scene_rollback for restoring), so differentiation from siblings is left to inference.

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 is implied by the read-only listing verb, but there is no explicit when-to-use, when-not-to-use, or alternative routing (e.g. 'to create a checkpoint use scene_checkpoint; to restore use scene_rollback'). An agent must infer its place in the checkpoint/rollback workflow.

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