audit_allowance_risk

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds the risk taxonomy being evaluated but not whether the analysis is purely offline over caller-supplied data or touches chain state — a meaningful distinction given openWorldHint=true. The bracketed capability/tier/API metadata is infrastructure detail, not behavior.

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 substantive sentence is tight and front-loaded after the bracket, but the leading "[Capability: available; tier: scout_limited_pioneer_full; API: ...; authority: ...]" block is runtime metadata that consumes attention without helping the agent act.

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 a nested object input at 0% description coverage, no output schema, and no explanation of input-vs-fetch semantics, the description is not sufficient to call this tool correctly. It should state what the allowances array contains and what the tool returns per risk class.

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% across a nested allowances array with six sub-fields (token, spender, allowance, amountUsd, requiredAmount, spenderVerified), and the description says nothing about any of them. Critically, it does not resolve whether walletAddress causes an on-chain fetch or is merely context for auditing the supplied allowances list — the single most consequential ambiguity for correct invocation.

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+resource ("Audit token approvals") and narrows scope to three risk classes: unlimited, unknown, and high-dollar allowance. That distinguishes it from generic siblings like simulate_transaction_risk and analyze_protocol_risk, though it never names an alternative.

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?

Usage is only implied by the phrase "Audit token approvals ... risk" — an agent can infer it's a pre-flight check on approvals, but there is no statement of when to call it versus simulate_transaction_risk or run_risk_sentinel, and no prerequisites or exclusions.

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