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

Annotations already declare non-readonly, non-idempotent, open-world, non-destructive behavior, so the bar is lower. The description still adds real value beyond them: a 2-credit cost charged only on success, and the fact that the result is asynchronous (a generation_id to poll). It does not mention failure modes or latency expectations.

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 short sentences, front-loaded with what is created, followed by cost and the follow-up tool. Nothing redundant; the cost disclosure is placed where an agent evaluating the call will see it.

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?

An output schema exists, yet the description still names the key return field the agent needs (generation_id) and the tool to use next. Combined with cost and reusability notes, an agent has everything required to call it correctly and handle the result.

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 both parameters (name, description) are already documented in the schema. The description's examples ('a wrench or a coffee cup', 'a red pipe wrench') illustrate the intended granularity of the description parameter but add no constraints or format detail beyond the schema. Baseline 3.

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 ('Generates') and resource ('a standalone object the mascot can hold or use') with concrete examples (wrench, coffee cup). This clearly separates it from create_pose, create_mascot, and create_animation in the sibling list.

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?

It provides clear downstream context — the returned generation_id feeds check_generation — and notes props are reusable across poses, which tells the agent not to regenerate per pose. It does not explicitly exclude or compare against siblings (e.g. when to make a prop vs. build it into a pose), so not a 5.

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