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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, establishing a safe, non-mutating, idempotent profile. The description adds that the tool is 'stateless' and 'one-shot', and enumerates output signals (verdict, risk score, instability/mechanism signals, recommendation). However, it does not describe validation requirements, error handling, or limitations beyond what annotations cover.

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?

The description consists of two sentences totaling about 28 words. It front-loads the core purpose and then succinctly lists inputs and outputs. Every clause contributes information, with no filler or redundancy.

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?

Given the tool complexity (8 parameters, no output schema), the description provides a useful high-level overview but omits detailed return structure and fails to position the tool relative to sibling 'cryptoguard_validate_trade'. The output components (verdict, risk score, etc.) are named but not elaborated, leaving interpretation gaps for the agent.

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%, with each of the 8 parameters having a description. The tool description groups inputs into 'training/test + optional what-if blocks', which is a high-level clustering but does not add new meaning beyond the schema. No additional parameter-level semantics are provided.

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 description clearly states the tool's purpose: a 'stateless decision bundle for one-shot trade gating' that produces a verdict, risk score, signals, and recommendation. It is a specific and informative statement of function. However, it does not explicitly differentiate from the sibling 'cryptoguard_validate_trade', relying on the 'Premium' label and extended output signals to imply a distinction.

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?

The description does not provide when-to-use or when-not-to-use guidance. It mentions 'one-shot' and 'full context' but never references alternative tools like 'cryptoguard_validate_trade' or 'cryptoguard_counterfactual_trade'. The 'Premium' adjective implies a more comprehensive option, but without explicit comparisons, the agent lacks direction on selecting this tool over siblings.

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