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

Annotations give the safety profile (destructiveHint=false, openWorldHint=true), but this description actively resolves the one thing annotations get wrong-looking: readOnlyHint=false on a read tool, explained as 'not marked read-only because each call is charged.' The pricing model, free-call carve-outs, and the 404/uncharged path for unknown hashes are exactly the kind of context structured fields cannot carry. Deductions for omitting response shape details such as unconfirmed/pending transactions and any pagination or rate-limit behavior.

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 purpose and return fields, then alternatives, then input format, then payment mechanics — a sensible ordering. The final sentence bundles pricing, card keys, free tier, and the read-only rationale into one dense run, which is informative but compressed enough to risk being skimmed past.

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 single-parameter lookup with no output schema, the description covers return fields, the error path, cost, and the correct sibling for adjacent questions. An agent has everything needed to decide whether to call it and to interpret a 404 without a follow-up.

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 format sentence largely restates the schema, but the concrete 64-hex example and the 'unknown hash returns 404, uncharged' rule add real meaning an agent cannot get from the schema alone. The example is especially valuable for a single opaque hash parameter, which is a common source of invocation errors.

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?

A specific verb ('Look up') applied to a specific resource ('Arbitrum One transaction by hash'), followed by an enumeration of the returned fields (sender, recipient, value, nonce, gas limit, selector, block). The network-qualified naming and explicit routing to arb_receipt and arb_logs make it distinguishable from every sibling without opening a schema.

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?

Gives an explicit use case ('see what was sent or whether it exists') and names two alternatives with the exact conditions that select them — arb_receipt for success/failure and fees, arb_logs for emitted events. This is the rare definition that fully closes the alternative-selection question.

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