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

Annotations only declare it is a non-read-only, non-destructive, closed-world call; the description adds the material facts: it spends workspace credits, requires human consent, can be refused for two specific reasons, and where the output lands (the task roll, retrievable via get_task). That is exactly the context annotations cannot express.

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 tight sentences, front-loaded with the cost warning, which is the most important information. A few compressed clauses ('read get_task again without seen then') sacrifice readability for brevity and cost the top score.

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?

No output schema exists, and the description compensates by explaining that results land in the task roll and are polled via get_task. Cost, consent, refusal, and recovery are all covered; only the exact mechanics of resubmitting after a left_out change remain ambiguous.

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?

With 75% schema coverage the schema already documents card, left_out, and accept_price; the description still adds real meaning by tying accept_price to the price the human agreed to and by framing left_out as the reason a call gets refused. The phrasing 'read get_task again without seen' is opaque and leaves the left_out re-submission flow partly unclear.

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: run one image or video card sourced from get_task. The scope (one card per call) and the credit-spending nature make it distinguishable from the surrounding get_task/start_task tools. It stops short of explicitly contrasting itself with start_task, which is the nearest ambiguous sibling.

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 preconditions (ask your human first, naming the card and its price), explicit failure conditions (price no longer matches accept_price, or the card now leaves out other images), and the recovery action (re-read get_task without seen). An agent knows when to call, when not to, and what to do on refusal.

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