Track Three.js scene changes: save a snapshot, then list added, removed, or modified objects in a read-only comparison.
[INSPECT] Read-only. Compare scene state over time: first call saves a snapshot, next call lists added/removed/modified objects.
| Name | Required | Description | Default |
|---|---|---|---|
| action | No | snapshot=save, diff=compare with saved, auto=snapshot if none else diff (default) |
Changes observed during successful MCP inspections.
v0.5.0Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / action / descriptionPrevious value: -"snapshot=save state, diff=compare with saved, auto=snapshot if none saved, diff if exists (default: auto)"New value: +"snapshot=save, diff=compare with saved, auto=snapshot if none else diff (default)"v0.4.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, destructiveHint=false, openWorldHint=false, so the safety profile is covered; the description usefully adds the stateful two-call workflow and what the diff reports. It omits snapshot lifecycle details (persistence, reset/overwrite, what happens if diff is called with no prior snapshot), and the order-dependent behavior sits in mild tension with idempotentHint=true, though the saved snapshot does not mutate the scene itself.
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 tight lines: the read-only classification is front-loaded and the mechanism follows immediately. Every clause earns its place, 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 one-optional-enum inspection tool with no output schema and full annotation coverage, the description supplies the essential mechanism and output content. Only edge cases (no prior snapshot, snapshot lifetime, detection granularity) are unstated, which is a minor gap at this complexity.
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% with a fully documented action enum, so the baseline is 3. The description adds meaning the schema lacks: the cross-call ordering contract (first call snapshots, subsequent call diffs) and the content of the diff output (added/removed/modified objects), which is genuinely additive.
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 gives a specific verb (compare/diff) and resource (scene state over time) and explains the snapshot-then-diff mechanism, which is unmistakable among the siblings. It does not explicitly distinguish itself from look-alikes such as scene_tree or pending_changes, so it stops short of a 5.
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?
"first call saves a snapshot, next call lists added/removed/modified objects" gives clear context for how the tool is driven across calls, but it never states when to prefer this over alternatives (scene_tree, pending_changes, object_details) or when it is inappropriate. Usage is implied rather than prescribed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.