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

Adds real context beyond annotations: the wait window and default, the polling loop, the side effect of saving the result into the user's library (consistent with readOnlyHint=false), and automatic refund on failure. Missing only edge behavior such as invalid job_id or rate limits.

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?

Three compact sentences, front-loaded with what the tool is, then timing behavior, then return values and failure refund. 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 carries the return contract itself (preview, new asset_id(s), png_url per sprite, sheet_url for animations/tilesets) plus the refund-on-failure rule, which is everything needed to call and interpret this 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 50%; wait_seconds is documented in the schema and the description reinforces its default and polling purpose. job_id's provenance is only implied via 'started with generate', so the description partially but not fully compensates for the bare schema field.

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 (status of a generation started with generate) and ties it directly to the producing sibling, so an agent can distinguish get_job from generate 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 explicit operational guidance: waits up to wait_seconds (default 25) and should be called again while still running, which tells the agent this is a polling tool. It does not name alternatives for retrieving finished assets (get_sprite_from_library, list_sprites), so it stops short of 5.

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