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

Goes well beyond the annotations: latest-block-only semantics, an 8 KB calldata cap, 422-with-reason on revert with no charge, and a $0.01/call price with the first 25 free. It even explains the idempotentHint=false consequence in plain terms ("each call is charged, so repeats are not free"), which is exactly the context annotations cannot convey.

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-loads the definition, then usage, then limits/pricing, which is a sensible order. There is some redundancy: "Reads or computes only and changes nothing" restates read-only (already in annotations) and the charging model is stated twice.

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 carries the return-value burden and does so ("raw return data", decode with the ABI), plus error and cost behavior. The only gap is the unmentioned `from` parameter, which the schema itself documents, so nothing critical is missing for correct invocation.

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 description coverage is 100%, so the baseline is 3. The description reinforces `to` and `data` with concrete example values and the decode step, but adds little beyond the schema and never mentions the optional `from` parameter or its msg.sender use case.

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 contract call on Linea (eth_call)") and immediately names the exact mechanics: ABI-encoded calldata in, raw return data out, no transaction or gas. It also carves itself out from the many linea_* siblings by saying it is for "any view function that has no dedicated tool," so an agent can tell it apart from linea_token_balance, linea_storage, etc.

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 says when to use it (view functions lacking a dedicated tool) and gives a worked example (USDC totalSupply, selector 0x18160ddd) plus the follow-up step (decode with the ABI). It does not name a specific sibling to prefer for common reads, but the "no dedicated tool" rule covers the exclusion adequately.

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