flow_create_scene

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose one genuinely valuable trait — that the default is a non-mutating 'prepare only' state and auto_confirm=true performs the real creation — but says nothing about permissions, side effects, idempotency, or what 'prepares only' actually produces or how it is later confirmed.

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 compact sentences with the core action, then the mode caveat, both front-loaded. Slightly awkward parenthetical phrasing keeps it from being a model of efficiency, but there is 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 six-parameter creation tool with no output schema and no annotations, the description leaves important questions open: what a 'prepared only' invocation returns, how project/campaign reuse interacts with scene creation, and what happens on failure. The rich schema compensates for parameter gaps, but the workflow behavior is under-explained overall.

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%, so all six parameters (prompt, campaign, characters, auto_confirm, project_name, reference_image) are already documented in the schema. The description restates characters/prompt and the auto_confirm behavior, adding no syntax, format, or constraint detail beyond what the schema already supplies; baseline 3 applies.

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: 'Create a new scene in Google Flow Scenes', and names the key inputs (characters, prompt). It is clearly distinguishable from non-creative siblings like flow_status or flow_list_models, though it does not explicitly contrast itself with the nearby flow_create_character.

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 explains the auto_confirm mode switch (prepare-only vs. actually create), which implies a two-step workflow, but gives no guidance on when to prefer this tool over flow_generate_video, flow_create_character, or the other creation siblings. Usage context is only partially inferred.

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