wallet_portfolio

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

Beyond the readOnly/idempotent annotations it discloses two behaviors an agent cannot infer: tokens outside the curated list are silently excluded (though stated in the response), and the paywall path where a missing key yields HTTP 402 carrying a decoded price quote rather than an error. That 402-is-not-a-failure note is genuinely useful for agent error handling; it stops short of describing pagination or response shape in detail, which the paid-access framing partly excuses.

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 what the tool returns, followed by an example, usage routing, and behavior notes. Slightly redundant in restating 'what a wallet holds in one call' from the opening, but every other sentence carries distinct information.

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 only two flat parameters and no output schema, the description covers the return contents (native + major tokens, USD prices, per-chain and total), the supported chain set, the curation limitation, and the payment requirement. An agent can call it and interpret failures correctly without further information.

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 coverage is 100% with only two parameters, so the schema already documents address/ENS and the chain choices. The description largely repeats those (the five chain names and 'Address or ENS name' duplicate the schema), adding only a concrete example URL as marginal value, so baseline 3 applies.

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 opening states a specific resource and scope: native balance plus major ERC-20 tokens across five named chains, with live USD prices and per-chain/total value. It also bounds the result set (curated token list) so an agent knows exactly what 'portfolio' means here, distinguishing it from single-balance and risk 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?

It gives an explicit use case ('one call' snapshot of holdings) and two explicit exclusions with named alternatives: chain_token_balance for a single token and wallet_check for counterparty risk. Nothing about tool selection is left to inference.

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