MCPFax On-Chain Toolkit

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

With no annotations, the description carries the full burden. It discloses that values are read at the latest block (reorg risk) and states the cost ($0.008 USDC per call via x402 on Base). It also implies a read-only operation by listing balance/nonce/code, and the optional token param adds behavioral context. Missing are error handling, rate limits, or idempotency, but the disclosed caveats exceed the typical baseline.

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 three sentences with zero filler. It front-loads the core purpose, then the optional parameter, then caveats and cost. Every sentence serves a distinct purpose, and the structure is logical for an agent to scan quickly.

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 no output schema, the description adequately conveys the return values (balance, nonce, contract status, optional token balance) and the operational context (chain default, cost, reorg risk). It doesn't mention response format or error behavior, but for a simple read-only call, the provided information is sufficient for an agent to invoke 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 the schema already documents each parameter. The description adds context for 'token' (reads ERC-20 balance in same call) and frames 'address' as a prerequisite for sending, which slightly enriches semantics. However, it doesn't add syntax, formats, or interaction details beyond the schema, so the value-add is marginal.

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 returns native balance, next nonce, and contract-code status, with an optional ERC-20 balance via 'token'. It uses specific resource nouns and implies a read operation, distinguishing it from token_info by focusing on address state rather than token metadata. However, it doesn't explicitly name sibling tools or contrast itself with them, so it's clear but not maximally differentiated.

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 gives a clear use case ('the three things needed before sending from or to an address') and explains when to pass 'token'. It does not explicitly state when to use alternatives like token_info or gas_now, nor does it mention any exclusions. The guidance is implied rather than explicit, so it's adequate but not prescriptive.

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?

The description mentions that the output is sorted by frequency and that it is free, but it does not disclose any side effects, rate limits, or how the data is sourced. With no annotations to fall back on, the description carries the burden and leaves much unspecified, especially the unclear 'categories' part.

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 short but poorly structured; the first sentence 'FREE, no payment.' is a fragment, and the final phrase 'with the categories nothing available yet' is syntactically incorrect. This detracts from clarity and conciseness.

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?

There is no output schema, so the description should clarify the return format, but it does not. It says 'aggregate' and 'most-requested first' without specifying the structure (e.g., list, counts, categories). The ambiguous 'categories' phrase further reduces completeness.

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?

The only parameter 'days' is well described in the input schema: it specifies the window in days, with default and maximum values. This fully explains the parameter's meaning and constraints, leaving no ambiguity.

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 that the tool provides an aggregate of what agents are looking for, sorted most-requested first, which is reasonably clear. However, the phrase 'with the categories nothing available yet' is garbled and introduces ambiguity about whether it returns categories or something else.

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?

Aside from the 'FREE, no payment' note, there is no guidance on when to use this tool compared to siblings like address_info or gas_now. It does not explicitly state scenarios where demand_report is preferable or when alternatives should be chosen.

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?

No annotations provided, but description fully discloses output details (wei, gwei, transfer cost) and the per-call fee of $0.005 USDC. No hidden side effects or contradictions.

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?

Though slightly long, every sentence adds value—purpose, units, usage timing, and cost. Logical flow from function to specific details makes it efficient 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?

No output schema, but description specifies exactly what data is returned (wei, gwei, transfer cost) and what it represents. Full parameter defaults and usage scenarios covered, leaving no gaps for the agent.

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?

The single 'chain' parameter is thoroughly explained with accepted values (Ethereum, Base, Arbitrum, Optimism, Polygon), comma-separated usage, example, and default. 100% schema coverage ensures full clarity.

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?

Clearly states it provides live gas price for multiple chains with specific units (wei and gwei) and includes transfer cost estimation. Distinct from sibling tools that focus on address, demand, tokens, 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 instructs to call immediately before sending a transaction due to fast gas moves, and explains how to pass multiple chains for comparison. Also mentions cost per call, giving clear timing and context.

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 full behavioral burden. It discloses that the request is free, that requests are catalogued, that nothing identifying is stored, and that the response includes availability and an MCP endpoint. This is transparent for a simple query tool, though it omits details like rate limits or what happens if the service is not available.

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 compact (three sentences) and front-loads the key value proposition ('FREE, no payment'). Each sentence adds distinct value: cost, purpose, and privacy/behavior. No redundant phrasing.

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 simple tool with one parameter, no output schema, and no annotations, the description covers the purpose, expected input, and a reasonable description of the response (availability and endpoint). It doesn't detail the exact response structure, but that is acceptable given the absence of an output schema and the tool's simplicity.

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% and the single parameter 'need' is described as 'What you are looking for.' The description adds a free-form context with an example, but does not introduce additional semantics beyond what the schema already conveys. Baseline of 3 is appropriate given the high schema coverage.

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's purpose: users describe what data they want, and it returns whether the service provides it, with an endpoint if available. It distinguishes itself from siblings by explicitly covering 'anything, not just on-chain data,' which differentiates it from the specific lookup tools like gas_now or token_info.

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 implies this tool is for general or unspecified data requests, contrasting with the more targeted sibling tools. It says 'anything, not just on-chain data,' which suggests using it when the specific tool is not obvious, but it does not explicitly name alternatives or exclusion conditions.

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 the full burden. It discloses error handling ('An address with no code, or a contract that is not an ERC-20, is reported as such'), states it is NOT charged on such failures, and mentions the cost ($0.005 USDC per call via x402). This gives agents a clear picture of behavior and side effects.

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 single paragraph that is efficient and front-loaded. It starts with the core purpose, then provides a compelling use case, then addresses edge cases and cost. Every sentence adds value with 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?

For a tool with only 2 parameters and no output schema, the description covers purpose, usage context, error handling, and cost. It also mentions the chain selection and defaults. There is nothing an agent needs to know to call it correctly that 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 description coverage is 100%, so both parameters (address and chain) are already documented. The description adds no new semantic details beyond the schema, e.g., it doesn't explain chain defaults beyond what the schema already says. 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?

The description clearly states a specific verb ('Read') and resource ('an ERC-20's name, symbol, decimals and total supply') and adds the scope of confirming code presence. It distinguishes itself from siblings like address_info and tx_status by focusing on token metadata retrieval, making the purpose unambiguous.

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 provides a concrete use case: 'Use before quoting an amount or building a transfer' and explains the risk of getting decimals wrong. While it doesn't explicitly name alternatives, the context makes the appropriate invocation clear. The instruction to use it before quoting amounts is strong guidance.

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 full burden. It discloses cost ($0.005 USDC per call via x402 on Base), the not_found behavior for unknown hashes, and lists the exact return fields. It implies a read-only operation but does not explicitly state that, nor does it mention rate limits or authentication. Still, the provided behavioral details are substantial and accurate.

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 two sentences, front-loaded with the core return fields, followed by a usage rationale, then the error/cost details. Every sentence adds value with zero fluff, and the most critical information (what it returns and when to use it) comes first.

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?

Although there is no output schema, the description explicitly lists the return fields (status, block, sender, recipient, value, gas used, fee paid, logs emitted), covers error handling (not_found), and notes the cost and payment mechanism. For a simple tool with two parameters, this is a complete and self-contained description.

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%: both 'hash' and 'chain' have clear descriptions, including an example and default. The tool description adds no additional parameter semantics beyond reinforcing that 'hash' is the transaction hash and 'chain' defaults to base. Since the schema already covers everything, 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?

Clearly states the tool returns transaction status (success, failed, pending) along with a detailed list of fields (block, sender, recipient, value, gas, fee, logs). This verb+resource specification distinguishes it from siblings like address_info or token_info, which are about other entities.

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 an explicit use case: 'Use to confirm an action you took really settled rather than assuming it did.' This gives clear context for when to invoke the tool. It does not explicitly state when not to use it, but the sibling tools are clearly different domains, so there is no ambiguity about alternatives.

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