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

With no annotations supplied, the description carries the full burden and does well: it discloses asynchronous execution with a named polling tool, per-image credit cost with the billing target (project owner), the skip-existing behavior, and how the first plate is derived when none exists. It omits failure/retry behavior and whether an existing plate can be regenerated or overwritten.

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?

Four tight sentences, front-loaded with the action and outputs, then cost, then async behavior, then the skip rule. Every clause carries information an agent needs; nothing is padding.

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 5-parameter, no-annotation, no-output-schema generation tool, the description covers the critical unknowns: cost, billing party, async polling, and view-skipping. Return shape is adequately implied by the polling pointer, though the result payload and per-view failure handling are not described.

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 only 20% (just 'label'), so the description must compensate. It adds genuine meaning for 'views' via the skip-unless-listed rule and implies 'imageModel' should be chosen via generation.list_models, but never explains how to pick a model or that 'label' only applies to the custom view.

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 ('Generate a location's reference plates') and immediately enumerates the concrete outputs (wide, reverse angle, detail) so an agent can distinguish it from character.generate_sheet, character.generate_view, and shot.generate_keyframe. The 'keeping one place' clause pins down the scope to a single location.

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?

Gives a real routing rule for the most common mistake: existing views are skipped unless explicitly listed in 'views', and it points to generation.list for polling and generation.list_models for cost. It stops short of saying when to prefer location.add_reference or location.update instead of generating plates, so it is clear context without explicit alternatives.

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