railx_preflight_trade

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

With no annotations, the description carries the full burden and does so well: it discloses the three possible verdicts, that the output is unsigned and therefore non-committing, that blocked plans contain nothing signable, and that a new plan consumes one checked-action unit (a cost/quota signal). It stops short of stating auth requirements, persistence of the plan, or how idempotencyKey affects retries.

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 filler, front-loaded with what the tool produces (a policy-checked verdict) and followed by the two facts most likely to change agent behavior: cost and the unsigned/unsignable guarantee.

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 tool with no annotations, no output schema, and 0% parameter coverage, the description covers the safety and cost profile but leaves the request shape and the returned payload undefined. An agent knows what verdict to expect but not what fields to supply or what the plan body contains.

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 mentions none of the four parameters (wallet, intent, idempotencyKey, slippageTolerance) or their meaning. The one quantitative statement ('one checked-action unit') is about billing, not parameters, so the description does not compensate for the total absence of schema-level parameter documentation.

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 compound action (build AND simulate a trade plan) plus the outcome space (allow/warn/block verdict), which is more informative than the bare name. It does not, however, distinguish itself from siblings like railx_create_quote or railx_simulate_transactions, which an agent could reasonably confuse it with.

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 'preflight' framing and the verdict vocabulary imply this is the step taken before committing a trade, which gives the agent an implied use case. But no alternative is named and no condition is given for choosing this over railx_create_quote or railx_simulate_transactions, so routing is left to inference.

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