What a stolen key would control: an agent's wallets at one block (free)

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

Annotations already cover read-only/idempotent/non-destructive, and the description adds substantive behavior beyond them: data confirmed on chain, refreshed every six hours from free public nodes, allowances capped at balance per token, unpriced tokens listed by symbol only, and an explicit schema-version tag. It also rules out a common misuse (treating the result as a forecast).

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?

Dense but front-loaded: the caller scope is stated first, then the returned fields, then the read cadence and the prediction caveat. Every clause carries information, though the single long middle sentence packs several concepts together and could be split for scanability.

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 does the heavy lifting by enumerating the return contents, their freshness, and their cost (free). It is close to complete for a read-only measurement tool; only edge behavior (e.g., what is returned for a wallet with no balances or allowances) is unaddressed.

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?

Both parameters are fully documented in the schema (100% coverage), so the baseline is 3; the description adds real value by clarifying they are alternatives — an agent id OR one bound 0x wallet address — which the flat schema does not express, along with the fact that neither is required.

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?

Names a specific resource (an agent's or bound wallet's on-chain exposure at one block) and enumerates exactly what is reported: priced stablecoin/token/ETH balances in USD, the EIP-7702 delegate with code hash and sweeper family, and open ERC-20 allowances. This is clearly distinguishable from siblings like pay_check, gate_check, or agent_stability.

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?

States the eligible callers (an L8-or-above agent or one of its bound wallets) and frames the result's purpose ('A measurement of exposure at one block, not a prediction'). It does not name alternatives or say when another sibling such as pay_check or gate_check is the better call, so it stops short of full when/when-not guidance.

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