Butterfly Delta Preflight

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

No annotations are provided, so the description must carry the burden. It does disclose that the tool is free and that it checks coverage/inspects an exact price, suggesting a non-mutating preview. However, it does not detail how coverage is determined, whether the price is guaranteed, or how the nested execution-policy fields affect 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?

The description is a single, direct sentence that front-loads 'Free' and packs in the core behavior (coverage check + price inspection) without unnecessary filler. Every clause contributes useful information.

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 free preflight preview tool, the high-level purpose is well captured, but there is no output schema. The description does not mention what the response will include or how the nested policy parameters influence coverage/price. Given the complexity of the trade input object, a bit more detail about what is done with the execution policy would improve completeness.

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% for the top-level trade object, which provides a solid baseline. The description adds context about checking the pair and preflight price, but it does not explain the semantic role of the nested execution-policy fields (thresholds, venue, side, etc.). The schema itself already carries most of the parameter meaning.

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 action ('check whether a USD spot pair is covered and inspect the exact $0.01 Base USDC preflight price'). It also signals free, read-only preview behavior before payment. It doesn't explicitly name sibling delta_preflight as the paid alternative, but 'before paying' distinguishes its purpose.

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 phrase 'before paying' implies this tool is a preliminary, free check prior to a paid delta_preflight call, but there is no explicit when-to-use/when-not-to-use guidance or reference to alternatives. A user can infer when to use it, but the instruction is not made explicit.

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

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

There are no annotations, so the description carries the full burden. It discloses the padegocal cost, the network, the fact that the verdict is signed, the live checks performed, and fail-closed behavior. This is useful but it doesn't describe return format or what the LLM must do with the signed PASS.

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 is 3 front-loaded sentences with no filler: cost, exact inputs, desired output, and fail-sf safety behavior. Every sentence earns its place and critical info appears early.

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?

Despite the absence of an output schema and annotations, the description covers cost, network, input cardinality, possible outcomes, and fallback behavior. It doesn't explain how the signed value should be used by the caller or how the mechanism relates to delta_pekeek, but for selecting and invoking the tool it declares enough.

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 already high, so the baseline is 3, but the description adds a meaningful focus instruction: send exact venue, side, and size and immediately before submission. It also maps the checks to the threshold parameters included in the nested trade object, helping the agent understand which values matter.

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 uses specific, action-oriented language: 'Gate a first crypto order before submission' and explains the tool returns a signed PASS, BLOCK, or UNKNOWN by running live checks. This is clearly distinguishable from a passive peek type tool, especially with the verb 'gate' and the pre-submission context.

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 says to send the exact order venue, side, and size immediately before submission, and states the tool fails closed on BLOCK or UNKNOWN. This gives a clear context for the pre-trade gating use case though it never explicitly compared to delta_peek or says 'do not use elsewhere'.

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