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

Annotations only flag it as a non-read-only, non-destructive, non-idempotent mutation; the description adds real behavior beyond that: a new PNG asset is produced (original preserved), the subject keeps its own colours, the tool 'does not use credits', and the result feeds patch_film. It does not note whether the operation is async or how long it takes, which is the remaining gap.

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?

Every sentence carries information (input constraints, output type, downstream step, sibling routing, cost) and the core action is front-loaded. Slightly dense with five clauses stacked on the first line, but 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?

With no output schema, the description supplies what an agent needs to act on the result ('Returns the new Asset ID: place it with patch_film'), covers cost, input suitability, and the sibling alternative. Nothing essential for correct invocation is missing for a two-parameter 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 only 50%: projectId is fully documented in the schema, but assetId has no description. The description partially compensates by framing the input as 'a ready image asset' the user uploaded, implying what assetId points at, and by stating the returned Asset ID's downstream use. Baseline 3 is appropriate for this coverage level.

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 (removes the background of an image asset) and the concrete output ('a new PNG image asset with a transparent background'). It also distinguishes itself from the sibling that does the analogous job for people, cutout_subject, so an agent can separate the two without opening either 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 use condition ('use it on a logo or product the person uploaded before it sits on footage or a colour') and names the alternative for a different input type ('for a person in a video, use cutout_subject'). No explicit when-not-to-use beyond that input-type exclusion, which keeps it short of a 5.

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