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

Annotations already declare mutation (readOnlyHint=false) and openWorldHint=true. The description adds valuable context—async execution, returns task_id and credit cost, and the model used—but doesn't cover rate limits or how to retrieve the result.

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?

Two tight sentences, front-loaded with the core action and model, then the return behavior. No wasted text.

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 burden of describing returns, which it partially does (task_id and credit cost). However, it omits how the async task is completed/polled, which is essential for an agent to use 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 description coverage is 100%, so all six parameters including the seed idempotency note and aspect default are documented in the schema. The description adds nothing about parameters, so baseline 3 applies.

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 (composes/edits keyframe image), names the model and resolution (GPT Image 2.5, 2K), and notes it's async. It doesn't differentiate from siblings like composer_generate_clip, but the purpose is unambiguous.

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?

No guidance on when to use this vs composer_generate_clip or other image tools, and no explicit instruction to follow up with composer_task_status. The phrase 'as an async task' hints at polling but leaves it to inference.

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