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

Annotations already mark it read-only/idempotent, and the description adds substantial behavioral context beyond that: it 'reads a stored image; it does not render or regenerate it,' explains thumbnail fallbacks (Workbench for unlit/dark/failed lit previews), notes historical thumbnails retain original settings, and tells agents to read thumbnailEngine/Framing/Size/Optics metadata. No contradiction with annotations exists.

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?

The description front-loads the core purpose well, but then becomes overlong and drifts into unrelated subscription/SSE/discovery metadata: 'On connection and release changes, modern subscriptions/listen sends the requested...' and 'The server cannot replace schemas retained by a host...'. Information about scene_apply's previewMaxSidePx is also repeated. Several sentences do not earn their place for a tool-invocation definition.

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?

Despite having no output schema, the description covers the output expectation ('inline image'), the main parameters and defaults, relevant behavioral policies (camera, lighting, engines, fallback, historical metadata), and sibling alternatives. It is complete enough for an agent to invoke scene_snapshot correctly in most contexts.

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. The description adds value by noting artifactId 'views any PNG artifact inline (a render_create result or a render_turntable frame)' and clarifying opticsObjectIds 'selects existing cached optical measurements; it does not resample the image.' These nuances go beyond the schema's description, though some parameter details are restated.

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 states a specific verb and resource: it shows a stored scene or PNG artifact as an inline image, and explicitly contrasts with rendering ('no render job'). It clearly differentiates from siblings like render_create ('Use render_create for fine detail...') and artifact_get by framing this as an inline snapshot viewer.

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?

The description gives explicit when-to-use guidance ('Snapshot after every mutation to verify visually before an expensive render') and names alternatives with conditions: 'For a fresh targeted query without rendering, use scene_apply with scene.analyze_optics' and 'Use render_create for fine detail, noise and final transmission quality.' No ambiguity remains about when to choose this tool.

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