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

Goes well beyond the annotations: calldata capped at 8 KB, reverting calls return 422 with the reason and are uncharged, pricing is $0.01/call via x402 USDC or card key with the first 25 free, and repeated calls are billed (matching idempotentHint=false). These are exactly the cost and failure-mode facts an agent needs before calling a paid endpoint.

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 it does and who it is for, then limits, error behavior, and pricing in a logical order. The pricing/auth sentence is long and could be tightened, but every clause carries information an agent needs (cost is the key differentiator for a paid tool).

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-parameter, no-output-schema tool this covers the full picture: input format, size limit, revert semantics, output being raw undecoded bytes requiring ABI decoding, and billing behavior. Nothing material is missing that would cause a misinvocation.

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; the description earns an extra point by adding a real constraint not in the schema (calldata up to 8 KB) plus a concrete to/data pair showing the expected format. It does not explain the optional 'from' parameter's msg.sender use case, which the schema already covers, so it stops short of a 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?

States a specific verb and resource — read-only eth_call on Polygon PoS that returns raw return data without a transaction or gas — and clearly separates it from the many polygon_* dedicated-tool siblings by framing it as the generic escape hatch. An agent immediately knows this is the low-level contract-read primitive.

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?

Explicit routing rule: 'Use to read any view function that has no dedicated tool', which both selects this tool and excludes cases where polygon_token_balance, polygon_nonce, etc. should be used instead. The worked example (USDC totalSupply, selector 0x18160ddd) and the 'decode the result with the function's ABI' follow-up step make the intended invocation pattern concrete.

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