aureon_propose_restoration

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

With no annotations provided, the description carries the full burden and does disclose meaningful traits: it is unsigned, does not sign or broadcast, requires both objectives to be 'manual', and returns 'to, data, and value for each step'. It omits auth requirements, whether any state is persisted, and any rate/limit behavior, so it is partial rather than complete.

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 short and front-loads the core purpose, and most sentences carry information. The closing sentence about the profit slice is confusing enough that it weakens rather than earns its place, pulling this below a clean 4.

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?

With no annotations and no output schema, the description must supply the behavioral and safety context itself. It gives a partial return shape and a precondition but omits authorization requirements and the relationship to the confirm step, which is critical for a financial restoration flow.

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 100%, so both parameters are already documented, making 3 the baseline. The description adds one semantic constraint ('Both objectives must be manual') that is not in the schema, but it does not clarify the weightBound ceiling/floor relationship beyond what the schema states.

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+resource ('Unsigned restoration from vault balances') is identifiable, and 'Does not sign or broadcast' implicitly separates it from the confirm_restoration sibling. However, 'sleeve cap' and 'stable reserve floor' are opaque domain jargon that the agent cannot decode, and the tool is never distinguished by name from aureon_get_restore_plan or aureon_confirm_restoration.

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?

There is a precondition ('Both objectives must be manual') but no when-to-use, when-not-to-use, or named alternatives among the many restoration siblings (get_restore_plan, confirm_restoration, restore_objective). The final sentence ('A full return to the sleeve cap is not the profit slice') hints at a constraint but is too cryptic to guide selection.

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