Start a video with Google Flow (spends credits)

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

With no annotations, the description carries the full burden and does so: it discloses credit spend, budget gating, the non-retry rule, and enumerates all four return states including which ones spend nothing ('over_budget' → nothing spent). The frames-vs-ingredients conflict path ('needs_answer, nothing spent') is exactly the kind of behavior an agent cannot infer elsewhere.

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?

Dense but nearly every clause carries decision-relevant information, and it is front-loaded with the shortcut framing and the credit warning. It is one long undifferentiated paragraph, though, so the return-state enumeration and the frames/ingredients rule are harder to scan than they should be.

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 16-parameter, no-annotation, no-output-schema mutation tool, the description covers cost, budget, return values, failure handling, follow-up tooling and parameter interaction rules. Nothing an agent needs to call this safely for the first time is missing.

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?

Adds genuine meaning beyond the 94%-covered schema: source_video is revealed to trigger an Omni video-to-video edit at 20 credits/720p, max_credits default is anchored to 'one 8 s Veo 3.1 Lite video', and role fields are explained as numbered to the agent. It does not touch model, characters, new_session, aspect_ratio or confirm_rights, but those are adequately described in schema.

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+resource ('asks the agent for a video and approves its quote') and frames itself as a composite shortcut for flow_chat + flow_approve, which immediately distinguishes it from those siblings. The cost implication ('SPENDS FLOW CREDITS') is front-loaded in the second sentence.

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?

Explicitly prescribes pre-call behavior ('tell the user the expected cost and check flow_credits first'), an exclusions rule ('never call it again to retry'), and a preference between parameters ('prefer them to plain attachments'). It also names the downstream tools to use per outcome (flow_wait, flow_chat), leaving little to inference.

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