FabTally Decode

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

With no annotations, the description carries the full burden and excels: it discloses the $0.002 fee, the x402 payment mechanism, the order of operations (challenge first, then settle), the proxy standards handled (EIP-1967/1822/OZ-legacy/beacon), and the verification sources (Sourcify or Blockscout). This is far more transparent than typical.

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?

Two dense sentences, front-loaded with the critical 'PAID' warning. All information earns its place: payment, inputs, outputs, proxy behavior, and fallback challenge. No fluff or repetition.

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?

Despite lacking an output schema, the description enumerates return values (ABI JSON, verification status/source, signatures, proxy-implementation ABI) and explains the 402 challenge fallback. It covers the essential aspects of a paid, multi-chain tool well enough for an agent to use it correctly.

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 baseline is 3. The description adds value by tying the parameters into the payment flow: 'Give {address, chain}' and 'pass x_payment to settle.' It clarifies the role of x_payment beyond the schema's description, making the interaction model concrete.

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 uses a specific verb ('fetch') and resource ('verified ABI + metadata for a contract'), and lists the exact outputs: ABI JSON, verification status/source, callable signatures, and proxy resolution. It clearly distinguishes from sibling decoding tools by focusing on ABI retrieval rather than data decoding.

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 explicitly explains the payment flow: omit x_payment to get a 402 challenge, then pass x_payment to settle. It implies when to use the tool (whenever a verified ABI is needed) but does not explicitly name alternatives or exclusions. Still, the context is clear and actionable.

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?

With no annotations, the description carries the burden and discloses the paid nature ($0.002 via x402), the challenge returned without payment, and the resolution sources. It doesn't mention error handling but covers key behaviors.

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?

Two sentences with front-loaded payment info, clear and compact. The shorthand input/output notation is efficient and adds no redundancy.

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, but the description explains the return value (resolved signature plus typed arguments) and the non-payment challenge. It covers the key aspects given the tool's complexity.

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 description adds marginal value. It summarizes the input format but does not explain x_payment beyond what the schema already provides. Baseline 3 is appropriate.

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?

Description clearly states it decodes a contract function call's calldata, resolving the 4-byte selector to a signature and decoding arguments. This distinguishes it from siblings like decode_log (logs) and selector_lookup (selectors only).

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?

Provides explicit input format 'Give {chain, to?, data, abi?}' and explains the resolution priority. It does not explicitly exclude alternative tools, but the specialization is clear from the description and title.

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?

With no annotations provided, the description carries full responsibility and does an excellent job. It discloses the paid nature ($0.003, x402, USDC on Base), the 402 challenge flow without payment, the use of x_payment to settle, the handling of complex parameter types (tuple/array/nested, anonymous events, indexed vs non-indexed), and the ABI resolution via Sourcify/Blockscout/4byte. This is far beyond minimal disclosure.

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 description is dense but every sentence earns its place. It front-loads the payment warning, then covers both usage modes, output details, ABI resolution, and the nondisclosure behavior. No filler, no redundancy, and structure follows a logical flow from payment to usage to behavior.

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 tool with no output schema, the description impressively covers return values (event name, canonical signature, named/typed args), the two invocation patterns, payment settlement, and ABI resolution. It is complete enough for an agent to invoke the tool correctly and interpret results, given the complexity of EVM log decoding.

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?

While the schema covers all 7 parameters at 100%, the description adds critical combinatoric semantics: it explicitly explains that chain is required and then either tx_hash OR address+topics+data must be provided, and that abi is optional. It also clarifies the x_payment flow and backward behavior, giving meaning far beyond the schema's individual field definitions.

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 clearly states the tool decodes EVM event logs to human-readable JSON, with a specific verb and resource. It distinguishes itself from sibling tools like decode_calldata (which handles calldata) and selector_lookup (which looks up function selectors) by focusing on logs and even calling itself 'FLAGSHIP' for that purpose.

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?

Provides clear context on when to use: two input modes are explained (tx_hash for all logs in a transaction, or address+topics+data for a single log). It also notes that ABI resolution is automatic, implying abi_fetch is not needed. However, it does not explicitly name sibling tools or provide 'when not to use' guidance, so it stops short of a perfect score.

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?

With no annotations, the description carries full burden and does an excellent job. It discloses the paid nature ($0.001, x402, USDC on Base), the use of external APIs (4byte.directory + openchain.xyz), the possibility of collisions, the verified flag, and the 402 challenge/settle 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?

The description is a compact paragraph with every sentence contributing essential information. It front-loads the critical 'PAID' warning, then states the core function, return characteristics, and payment flow without redundancy.

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 annotations, the description provides sufficient context: input format, output highlights (all matches, verified flag), payment mechanics, and the challenge/settle flow. This is adequate for an agent to use the tool correctly without additional documentation.

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 parameters are already documented. The description adds meaningful context for x_payment (forwarded as X-PAYMENT header, omitted to obtain challenge) and clarifies the selector format. It doesn't add much beyond the schema for selector but the payment parameter behavior is valuable.

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 action: resolve a 4-byte function selector or 32-byte event topic hash to human-readable signature(s). It clearly distinguishes from sibling tools like decode_calldata and decode_log by focusing on signature resolution rather than data decoding, and mentions the external directories used.

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?

Clear context is provided: when to use (given a selector/topic, to get signatures), and the payment flow is explicitly described (without payment you get a challenge, pass x_payment to settle). However, it does not explicitly mention when not to use or compare against the sibling tools, so it stops short of a 5.

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