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

Annotations already declare readOnlyHint=true, so the read-only nature is known. The description adds useful behavioral context about the return contents (spenders, USD exposure, protocol attribution, and hacked/abandoned flags) and the broader scope relative to the sibling. No destructive behavior is implied, and no contradiction 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 two sentences, front-loaded with the core purpose, then return highlights, then a comparative pointer. Every sentence earns its place with no redundancy or fluff.

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 an output schema present, return values are documented. The description covers what the tool does, its chain scope, the parameters (implicitly), the type of data returned, and its relationship to a key sibling. This is complete for an agent to select and call the tool.

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 input schema already describes both parameters with 100% coverage. The description adds no additional parameter-level detail beyond tying 'wallet' and 'chain' to the context. Baseline 3 applies because the schema carries the semantics.

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 clearly states the tool inspects a wallet's ERC-20 token authorization exposure on a specific chain, with a specific verb ('inspect') and resource. It also immediately distinguishes itself from the sibling get_token_approvals by noting it is broader, so an agent can differentiate.

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 description provides a clear alternative by comparing to get_token_approvals and characterizing it as 'curated block-accurate', implying when the narrower tool is appropriate. However, it doesn't explicitly state 'use this when' or 'do not use when', leaving some inference to the agent.

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