production.qa_render_multiview

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond that: a checkpoint is taken and scene settings are restored, implying the scene is left as found. It does not say where previews are written, what 'lightweight' means in resolution/quality terms, or what the checkpoint lifecycle is.

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?

It is a single front-loaded sentence with no filler, which is good, but the terseness is under-specification rather than economy given zero parameter documentation and no usage routing. The key behavioral facts (checkpoint, restore) are buried in a trailing participial phrase.

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?

An output schema exists, so return values need not be explained. However, for a 3-parameter mutation-flagged tool with 0% schema coverage and many overlapping siblings, the description leaves too much unstated: parameter roles, output location, and why to pick this over the other preview tools.

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 0% across all three parameters (object_name, options, operation_id), so the description must compensate and does not. It never mentions which object is rendered, what belongs in the free-form 'options' object (view angles? resolution?), or whether operation_id ties to the checkpoint/operation tracking. The FRONT/SIDE/THREE_QUARTER mention hints at configurable views but is never mapped to a parameter.

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 identifies the output (lightweight FRONT/SIDE/THREE_QUARTER previews) and two traits (checkpointed, restored scene settings), but it is a noun phrase with no verb and never distinguishes itself from close siblings like qa_render_preview, qa_capture_viewport, or character_render_multiview. An agent can guess it renders multi-angle previews but cannot tell why it exists alongside those tools.

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?

There is no when-to-use statement, no prerequisite, and no mention of any alternative despite at least three sibling preview/capture tools that overlap. The agent must infer usage purely from the word 'previews'.

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