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

Annotations declare destructiveHint=true and non-idempotent, and the description earns that with concrete financial consequences: the $0.25 max tier is charged upfront, unused difference is recorded as owed and not auto-refunded on x402, while Arc escrow captures only the used tier via reclaim(). It also notes that a ticker pulls extra paths *before* charging, a non-obvious ordering side effect.

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?

Front-loaded with the core purpose, then pricing, then rail-specific refund behavior — every sentence carries operational weight. It is dense and parenthetical-heavy (e.g. '$0.25 max tier ... (not yet auto-refunded)'), which slows parsing slightly but does not waste space.

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 output schema, the description still names the returned components (consensus, coherence 0-1, pass/block) and covers pricing, refund asymmetry, and the 32-path cap — enough to call it safely. What is missing is the response envelope or error behavior when the gate blocks, which matters for a paid call.

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 descriptions are already 100% covered, so the baseline is 3; the description adds meaning beyond them by explaining that ticker/sources expand the path set before pricing and by contrasting the arc_auth_id and payment_header rails. Path-level field requirements are left to the schema.

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 verb and resource: scores whether trading-signal paths agree, producing a confidence-weighted consensus, a coherence 0-1 value, and a pass/block gate. The scope (max 32 paths, paid gate) is unmistakable and separates it from smoke/generic siblings.

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?

Gives the pass criterion (non-flat consensus plus coherence at or above the threshold, default 0.6) and tier boundaries, so the conditions for a useful call are inferable. It never names an alternative tool (e.g. leviathan_interfere or spend_gate_check) or states when *not* to use this gate, leaving routing to inference.

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