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

With readOnlyHint=true the safety bar is low, and the description goes far beyond it: it discloses edge-case semantics (chainsNotServed yields an empty result that "is not an answer about that chain"), warns that a sole unsupported chain returns "no totals" so "a zero would read as a real balance", and explains the v3/v4 behavioral difference plus the meaning of "marketsWithPosition": 0. No contradiction with the readOnly annotation.

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 the core purpose; every sentence carries a distinct behavioral or routing fact with no filler. It is long (~200 words), but the length is proportionate to the v3/v4 and multi-chain complexity, and the prose is dense rather than padded.

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 tool with no output schema, the description covers the critical return semantics (v4 fields, v3 per-market entries, scope-only replies) and the main misinterpretation traps. It doesn't specify the exact response JSON shape or invalid-address behavior, which is the only notable gap given the complexity.

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%, so the baseline is 3, but the description adds real meaning: it explains the consequence of omitting chainId (both versions cover every chain, no looping) and what choosing v3 vs v4 changes in the output. It stops short of defining response syntax or parameter format details beyond the schema, so 4 rather than 5.

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?

Opens with a precise statement of the resource — "A wallet's aggregate position and health factor" — which is specific and immediately separates it from siblings like get_user_positions (detailed positions) and get_user_summary_history (history). The title reinforces the same resource, and the body pins down exactly what is returned for v3 and v4.

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?

Explicitly routes to an alternative: "For what it holds, pass 'user' to get_markets, which returns walletBalance per reserve" — a clear when-not/alternative rule telling the agent where to get token balances instead. It also gives direct usage instruction not to loop over chains: "there is no need to loop over chains yourself."

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