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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description still adds real value beyond them: it flags contract creation (null to) and pending transactions (null block) instead of forcing inference, and specifies the found:false semantics for unknown hashes. Pricing and payment mechanics ($0.002/call, x-credit-token header, 1 free call/day, no API key) are also disclosed, though auth/rate-limit behavior is only lightly touched.

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?

The purpose is front-loaded in the first clause, followed by return fields, edge cases, and pricing in a logical order. It is somewhat long at six sentences, and listing value 'in wei and ETH' is mildly redundant, but nearly every sentence carries distinct information (edge flags, error semantics, pricing).

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 an output schema present the description needn't explain return values, yet it still summarizes fields and, more importantly, covers the behavioral gaps an agent needs: edge-case flags, not-found semantics, and payment requirements. Nothing an agent needs to invoke base_tx correctly is missing.

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% for the single 'hash' parameter, so the schema already carries the semantics. The description restates that hash is required but adds no format guidance (hex length, 0x prefix) beyond what the schema provides, so baseline 3 applies.

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?

The description states a specific verb+resource: fetch a Base transaction by hash, returning it 'exactly as the chain has it — unedited.' The explicit field enumeration (from, to, value in wei and ETH, nonce, gas, fee caps, type, method selector) makes the scope unambiguous. It distinguishes itself implicitly from decode/explain siblings via the 'unedited' framing, but names no sibling explicitly, so it lands just short of a 5.

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?

It states the required input ('Required input: hash') and clarifies that unknown hashes answer found:false rather than erroring, which is useful edge guidance. However, it never says when to reach for base_tx versus base_receipt, tx_decode, or ai_tx_explain, so usage is only implied.

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