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

Beyond the annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true), the description adds real operational context: the action is paid, it requires a 'signed wallet invocation,' and a delivered replay is free/idempotent. That payment and idempotency context is exactly the kind of detail annotations cannot express. It stops short of explaining what is destroyed or the failure modes for a partial payment.

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 with no obvious padding, and the primary action is front-loaded. The trade-off is that the terseness tips into jargon ('Existing text/model', 'Public images', 'Provider effect') that costs more in ambiguity than it saves in words.

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?

For a paid, state-changing tool with no output schema and 0% schema description coverage, the description leaves the parameters and the return/result path unexplained. It says a replay is free but not what a successful first run returns or how the caller learns fulfillment status, forcing reliance on sibling tools by guesswork.

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 0% and the description never explains the two parameters. order_id has a strict pattern (^csc-[0-9a-f]{64}$) and the 'purchase' parameter is an unexplained empty object; the only adjacent hint is 'do not pay again,' which loosely implies purchase relates to payment. The description does not compensate for the coverage gap.

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?

The verb 'execute' and resource 'CSC' (China Supply Check) are present, so the core action is inferable. However, the description is bracketed into cryptic branches ('Existing text/model' vs. 'Public images') that muddy what the tool fundamentally does, and it never plainly states 'runs a paid China Supply Check.' It is not tautological, but the purpose is only partially clear.

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 gestures at two usage modes and warns 'delivered replay is free, do not pay again,' which is genuine when-to-use guidance. But it does not name the obvious alternatives in the sibling set, such as purchase_china_supply_check_v0, status_china_supply_check_v0, or result_china_supply_check_v0, so the agent must guess how this differs from them.

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