Base Transaction Decoder

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

Despite annotations already declaring readOnlyHint=false, and destructiveHint=false, the description goes far beyond them by disclosing the financial cost, the payment mechanism (USDC on Base via x402), the quota cap, the token-based proof of purchase, and the fact that no account is needed. It also explains what the token is used for, which is critical behavioral context.

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?

Three sentences deliver a wealth of information without redundancy: what the pass costs, what it grants, how to use the returned token, and how to renew. The most important facts (price, quota) are front-loaded, and every clause earns its place.

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?

Given there is no output schema and no parameters, the description is remarkably complete. It tells the agent exactly what the tool returns (a bearer pass token), how to attach it, that the token is the only proof of purchase, and when to repurchase. Nothing an agent needs to call or use this tool effectively 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?

There are zero parameters and schema description coverage is 100%, so the schema already provides all parameter information. The description adds nothing about parameters because none exist, and that is appropriate. A baseline of 4 applies here.

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 ('Buy'), a clear resource ('30-day pass'), and includes concrete details about price, currency, network, and the exact benefit (up to 10,000 explain_transaction calls). It also implicitly differentiates from the sibling tool explain_transaction by explaining that this pass removes per-call payment.

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?

The description clearly communicates the context: you buy this pass when you expect to make many explain_transaction calls without per-call payment, and you renew after expiry. It does not explicitly name the alternative of paying per-call directly via explain_transaction, but the 'no per-call payment' phrase strongly implies it.

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

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

Goes far beyond the readOnly/idempotent annotations: discloses that risk checks fail open and that an empty risk_flags with a non-ok check status means 'not checked, not clean', that gas_price_basis='latest' is non-reproducible, that a partial field exists, and that provenance.untrusted_fields carry author-controlled strings to be treated as data only. These are exactly the caveats an agent would otherwise get wrong.

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 required input before the response shape and pricing. Nearly every clause carries information, but it is delivered as one dense run-on paragraph with parenthetical pile-ups (risk_flags, provenance, pricing) that would read far better as short lines.

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?

No output schema exists, so the description must carry the return contract, and it does: every notable field, the partial/provenance escape hatches, the fail-open semantics, and the reproducibility caveat are covered. Nothing an agent needs in order to call this correctly or interpret the result 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?

One parameter at 100% schema coverage, so the schema already carries the format ('0x + 64 hex characters'). The description only restates 'Input: a transaction hash' and adds no syntax or validation detail beyond it; 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?

Opens with a specific verb and resource ('Explain a Base-mainnet transaction in plain English') and immediately names the required input. The chain scope (Base mainnet, chain id 8453) is stated twice, and it is trivially distinguishable from the only sibling, buy_pass.

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 scope exclusion ('Base mainnet only'), explicit free-tier boundary (50 calls per 24h), and explicit routing to alternatives: retry with x402 payment, POST /explain over plain HTTP, or buy_pass for heavy use. An agent knows exactly when this tool applies and what to do when it doesn't.

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