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

Annotations only declare readOnlyHint=true, but the description adds extensive behavioral context beyond that: the audit is block-accurate, flags unlimited approvals by risk level, covers only tracked assets/curated spenders, does not inspect NFT or Permit2 approvals, and uses an error field to mark incomplete results rather than returning a clean bill of health. No contradiction with the readOnly annotation exists.

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 denser than necessary and has slight redundancy ('block-accurate' appears twice, and 'use get_wallet_approvals instead' appears in both the Use-when and Alternatives sections). However, the labeled sections — Use when, Limitations, Alternatives — make it scannable and every sentence adds useful selection or behavioral detail.

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?

Given the tool's complexity, the description covers what the tool audits, when to use it, what it misses, and how errors are signaled, while the output schema handles return-value structure. All parameter meanings and defaults are available in the schema, and the limitations are explicit. An agent has everything needed to invoke it correctly.

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?

The schema already documents all four parameters (100% coverage), and the description goes further by adding useful semantics: curated spender names, the risk-level classification, max allowances of 50 tokens and 20 spenders, and the exclusion of untracked tokens/custom spenders. This materially helps an agent choose correct values beyond the raw 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?

The description opens with a precise verb+resource: 'block-accurate audit of ERC-20 allowances for a wallet across curated DeFi spenders.' It names the exact protocols, chains, and risk classification behavior, and explicitly contrasts itself with the sibling get_wallet_approvals, so an agent can distinguish it without opening schemas.

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?

It gives concrete triggers ('Use before swaps or after security incidents'), a direct 'Use when' statement, and an explicit alternative: 'For broad all-chain spender discovery... use get_wallet_approvals instead.' The 'Alternatives' section reinforces routing with assess_counterparty_risk. This leaves no ambiguity about when to select this tool.

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