Run a one-click effect on a photo

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

Annotations only say readOnly=false, destructive=false, openWorld=true, idempotent=false; the description adds the critical behavior the agent cannot infer — that calls without confirm are a free quote and confirm:true triggers real spend, plus a second paid step for the 5-second clip. It also flags the likeness policy for real people's photos. It stops short of describing whether the render is synchronous or a polled job (relevant given get_job/resume_job siblings), so not a 5.

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?

Front-loaded with the purpose and effect catalog, then a compact sequence of call patterns; nearly every clause carries routing or gating information. The telegraphic style ('`effect` alone: what it takes') is efficient but slightly opaque on first read, keeping it off a 5.

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 9-parameter, nested-object, multi-step tool with no output schema, the description covers the full workflow including both paid stages and the free-quote gate. The main gap is that it never says what a 'quote' returns or how to retrieve the finished asset after confirming, which matters for a generate-and-wait tool.

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 a 3 is the floor; the description earns above it by explaining how parameters combine into distinct operations (effect+images vs effect+still) and what `describe` and `confirm` mean in the flow. It still leaves `options`/`text`/`speech`/`aspectRatio` largely to the schema, which already documents them.

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 concrete verb and resource ('a photo goes in, a styled picture comes out') and enumerates actual effects (plush toy, 3D figure, bullet time, outfit swap, relight) so the agent knows the domain instantly. It also names the sibling it is not ('For a look not on the list use generate_image'), separating it from generate_image/edit_image without opening a schema.

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 an explicit call matrix: no `effect` = free list, `effect` alone = requirements, `effect` + `images` = free quote, add confirm:true = make the picture, `effect` + `still` = clip quote, confirm:true = make the clip. It also routes out-of-list looks to generate_image, so both when-to-use and when-not-to-use are covered.

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