accounts / balances

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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, but the description adds two things they don't: all results are read at one pinned chain block (a consistent snapshot rather than a series of live reads) and there is no token discovery. That is genuine behavioral context. It doesn't say what happens on invalid or unlisted tokens, or whether the pinned block is the latest.

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?

A single well-formed sentence with the capability first and the exclusion in a trailing parenthetical. No filler and nothing buried.

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?

For a 3-required-parameter tool with no output schema, the definition covers the core contract (explicit tokens, one pinned block, max 32) which is enough to call it. But it omits token address format, chain_id expectations, and whether the pinned block is fixed at latest, all of which the agent must guess.

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 0%, so the description must carry parameter meaning. It explains 'tokens' as an explicit caller-supplied list capped at 32 (partly redundant with maxItems: 32) but says nothing about the expected format (contract addresses?), nothing about 'chain_id' (no indication of supported IDs or which registry lists them), and never mentions 'wallet' at all beyond the implication of 'balances'.

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?

Specific verb ('Read') plus resource ('token balances') with a clear scope: explicitly supplied tokens only, capped at 32, evaluated at a single pinned block. The parenthetical explicitly excludes portfolio discovery, so the agent knows this is not an enumeration tool. It stops short of naming a sibling such as accounts.positions as the 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?

The phrase 'explicitly provided' and 'no automatic portfolio discovery' implies the caller must already know the token list, which is real usage guidance. However, it never states when to prefer this over accounts.positions or which call to make when discovery is needed, leaving the routing decision implicit.

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