Taskmarket Onchain API

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

With no annotations, the description carries the full burden and does disclose important traits: a bounded result window, newest-first ordering, and a per-call cost ($0.02 USDC on Base via x402). It omits failure behavior (invalid address, unsupported chain) and whether payment is charged on empty results.

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: the first front-loads what the tool returns, the second front-loads the cost constraint. No filler and no repetition of the tool name.

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 5-parameter read tool with no output schema and no annotations, the description covers return contents, ordering, window bound, and pricing. What is missing is practical invocation detail: no guidance on choosing chain/token combinations or on narrowing an address's history when the window is too small.

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 60% (chain, token, address documented; limit and blocks undocumented). The description only vaguely gestures at the 'blocks' parameter via 'bounded' and adds no format, default, or range meaning beyond the schema, so it neither compensates for nor worsens the gap.

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?

States a specific verb+resource ('List recent ERC-20 transfers involving an address') and adds concrete scope details (bounded, newest first) plus the returned fields. It is not confused with wallet_balance or tx_status, but it never explicitly contrasts itself with those siblings.

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?

There is only an implied use case: 'recent' activity lookups. The description gives no explicit when-to-use, when-not-to-use, or pointer to alternatives (e.g. tx_status for a single hash, wallet_balance for holdings), despite three closely related siblings.

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 supplied, the description carries the full behavioral burden, and it does disclose a significant trait the schema cannot: this call is monetized at $0.01 USDC on Base via x402, so the agent knows a payment flow is involved. It omits other relevant behaviors — how pending/unconfirmed or unknown hashes are handled, whether a failed read still charges, and any rate limits — so it is partial rather than complete.

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, both earning their place: the first front-loads the returned data, the second front-loads the payment requirement. Nothing is repeated from the schema and there is no filler.

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 two-parameter read tool with no output schema, the description effectively stands in for the missing return documentation by enumerating the fields returned and the explorer links. It also surfaces the paid-call requirement, which the structured fields do not; only edge-case behavior (pending transactions, error paths) is left unaddressed.

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% with only two parameters, and the schema already documents the enum of chains and the 0x-prefixed hash format. The description adds no parameter-level meaning (e.g., default chain behavior or cross-chain caveats), 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 names a specific verb and resource ('Get a transaction's status') and enumerates exactly what comes back: block, timestamp, from/to, value, gas used, fee, and explorer links. It does not, however, distinguish itself from the sibling verify_receipt, which plausibly covers overlapping receipt data, leaving the agent to infer the boundary.

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?

There is no when-to-use guidance and no mention of the siblings (address_activity, verify_receipt, wallet_balance). The only situational information is the payment note, which tells the agent what it costs but not when to prefer this tool over verify_receipt for receipt-shaped data.

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 and does disclose key behavior: the four possible outcomes (MATCH/MISMATCH/NOT_FOUND/ERROR), that on-chain evidence accompanies the result, and that the call is paid ($0.02 USDC on Base via x402) — a cost an agent must know before invoking. It stops short of stating that it is read-only, whether paid calls are charged on ERROR, or any rate limits.

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 short sentences, front-loaded with purpose, then return contract, then cost — no filler or 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?

With no output schema, the description correctly compensates by enumerating the return statuses, and it flags the payment requirement. Minor gap: it does not clarify that the paid-on-Base model is distinct from the `chain` parameter that allows reading bsc/ethereum/polygon.

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 all five parameters are already documented in the schema; the description adds no syntax, default, or format detail beyond restating recipient and amount matching. 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?

Uses a specific verb ("Verify") on a specific resource ("on-chain payment/transfer") and states the comparison basis (expected recipient and amount), which separates it from the sibling tools like tx_status (raw status) or wallet_balance (balance lookup).

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 phrase "Verify an on-chain payment/transfer against an expected recipient and amount" implies the use case, but there is no explicit when-to-use, when-not-to-use, or naming of the sibling alternatives such as tx_status for a plain status check.

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 zero annotations the description carries the full burden, and it does disclose two real behavioral traits: the paid x402 model with a concrete price, and that results come with explorer evidence. However it omits failure behavior (unreadable decimals, unsupported token), any latency or rate-limit context, and the advertised block-pinning is not reflected in any parameter, leaving the actual snapshot semantics unclear.

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 short sentences, front-loaded with the operation and followed by the payment constraint, with no filler. The only inefficiency is the "pinned to a block number" clause, which promises a capability the schema does not expose and thus spends words on a misleading detail.

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 four-parameter read tool with no output schema and no annotations, the description covers the essentials of what is read and what it costs, which is reasonable. It falls short on return shape (what "explorer evidence" comprises) and on the undocumented block-pinning behavior, which an agent would need in order to interpret determinism of results.

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 baseline is 3 regardless. The description restates the token choices already documented in the `token` schema field and adds nothing about `chain` values or the `tokenDecimals` fallback path, so it does not materially extend parameter meaning.

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 pairs a specific verb ("Read") with a precise resource ("a wallet's decoded balance") and enumerates the token scope (native, USDC, any ERC-20). That is enough to distinguish it from siblings like address_activity and tx_status, though it never names them explicitly and adds a confusing "pinned to a block number" claim that has no corresponding parameter.

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?

There is no statement of when to prefer this over address_activity or verify_receipt, no prerequisites, and no exclusions. The only usage-relevant information is the cost line ($0.01 USDC on Base via x402), which tells the agent a payment is involved but not when the tool is the right choice.

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