Aether: Base onchain data & token risk (x402)

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds valuable cost and payment context: $0.25 USDC on Base via x402. But it does not explain what 'bounded' means, whether the audit is rate-limited, or what happens after payment, so it adds only moderate 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?

Two short sentences, front-loaded with purpose and followed by the essential commercial constraint. No words are wasted, and the paid nature is surfaced immediately.

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 explain what an audit returns, but it only says 'audit' without listing outputs. Combined with the unexplained 'request' parameter and absent usage guidance, the definition is too thin for a paid openWorld tool.

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 0%, so the description must carry the burden. It implies the 'text' parameter is the supplied technical text, but it says nothing about the 'request' parameter, its purpose, or any formatting constraints beyond the schema's maxLength.

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 and resource: 'Bounded deterministic audit of supplied technical text.' An agent can tell it audits text rather than blockchain data. However, it does not differentiate from sibling audit_x402_payability, nor does it clarify what 'bounded deterministic' means in practice.

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 no when-to-use, when-not-to-use, or alternative tool guidance. It does not mention audit_x402_payability or any other sibling, leaving the agent to infer when this audit is appropriate versus a narrower one.

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?

Annotations already declare readOnlyHint and openWorldHint, but the description adds a genuinely load-bearing trait they don't cover: this is a paid call costing $0.01 USDC on Base via x402, and it returns a fix for every failure. That cost disclosure is exactly the kind of context an agent needs before invoking. It stops short of noting rate limits or result structure.

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, front-loaded with the tool's identity and check list, with the price disclosed last. It is dense but every clause (the enumerated checks, the fix guarantee, the cost) earns its place; 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?

No output schema exists, so the description carries return-value burden, and it does so partially by enumerating the checks and promising a fix per failure. Given the rich 5-parameter schema and read-only/open-world annotations, an agent has enough to call it, though result formatting and failure-report shape remain unstated.

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 schema already documents url, body, expect, method, and headers with defaults and constraints. The description adds no per-parameter syntax or format guidance beyond the general 'probes an x402 endpoint' framing, so the baseline of 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?

States a specific verb (probes/checks) and resource (an x402 endpoint's 402 challenge) and enumerates exactly what it inspects — CAIP-2 network, USDC asset, payTo checksum, amount, EIP-712 domain, resource URL, Bazaar discovery. This is far more specific than any sibling and an agent can distinguish it from audit_evidence or score_opportunity immediately.

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?

Usage is implied — you audit an x402 endpoint to verify it is payable before integrating or paying — and 'with a fix for every failure' hints at the remediation value. But it never names when to prefer this over siblings (audit_evidence, score_opportunity) or states preconditions/exclusions explicitly.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful context beyond that: the paid cost ($0.002 USDC on Base via x402) and the semantics of the returned allowance. It does not mention rate limits, caching, or failure modes, keeping it at a 3.

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 compact sentences: the purpose first, then the usage cue in parentheses, then the price. Nothing is wasted, though bundling the cost note into its own sentence adds little to call-time decisions.

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 read-only three-parameter allowance lookup with no output schema, the description covers purpose, usage context, and pricing. It falls short on explaining the return value's formatting (raw wei vs. decimal) and on documenting the individual address parameters, which is a real gap at 0% schema coverage.

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 0%, so the description must carry parameter meaning. It partially compensates by describing the relational roles (spender moving from an owner's ERC-20 balance) and the token reference, but gives no per-parameter explanation, format, or constraints beyond the visible address regex.

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 the specific resource (ERC-20 allowance) and states exactly what the return value represents: how much a spender may move from an owner's balance. It is clearly distinguishable from balance siblings like base_erc20_balance, though it does not explicitly name them.

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 parenthetical '(approval check before swaps or revokes)' gives concrete when-to-use context, which is more than most tool definitions offer. It stops short of naming an alternative tool or stating exclusions, so it does not reach a 5.

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?

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely new behavioral context that annotations cannot express: this is a paid call costing $0.001 USDC via x402. It stops short of explaining whether payment is automatic or how settlement works, so it is not a full 5.

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, zero filler, and the primary capability is front-loaded ahead of the pricing note. Nothing could be removed without losing information.

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 single-parameter read tool with safety annotations, the description covers what it does, the chain, and the cost. It omits the return-value format (wei vs decimal ETH) and the actual payment mechanics, and with no output schema and no parameter description, those gaps are left entirely to the caller.

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 0%, so the description carries the burden; "any Base address" does clarify that the input is a Base-network address rather than an arbitrary string. However, it adds no format, casing, or checksum detail beyond the regex already in the schema, leaving the one required parameter thinly documented.

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?

"Native ETH balance of any Base address" states a specific verb (return balance) and resource (native ETH) plus the chain scope. The word "Native" implicitly distinguishes it from the ERC20 sibling `base_erc20_balance`, so an agent can route without opening the schema.

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?

No when-to-use guidance, no prerequisites, and no alternative named. The description never tells the agent when to prefer this over `base_erc20_balance`, `base_portfolio`, or `base_call`; the agent must infer it from the word "Native".

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?

Annotations already mark this read-only and open-world, so the safety profile is covered. The description adds genuinely useful context beyond that: the return contents (avatar, profile text records) and, importantly, that it is a paid call at $0.003 USDC on Base via x402.

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 tight sentences: the action and output first, then the payment prerequisite. Nothing is padded and the payload is front-loaded.

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 single-param, no-output-schema tool, the description covers input format, output contents, and cost. It stops short of covering payment mechanics (automatic vs. manual x402 settlement) and failure behavior for unregistered names, which keeps it from a 5.

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 0%, so the schema gives no help for 'name' beyond type and length bounds. The description compensates with a concrete format example (jesse.base.eth), which is the key semantic detail needed for a single, otherwise self-evident parameter.

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 (Resolve) and resource (Basename, with example jesse.base.eth) and names the output (address plus avatar and profile text records). No sibling tool performs name resolution, so an agent can place it immediately.

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 when to use it (you have a .eth-style name and need the underlying address) and adds a cost signal, but never states when to prefer it over alternatives or what happens for unresolvable names. Usage is inferable rather than explicit.

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?

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds valuable non-annotation context: the tool is paid ($0.001 USDC on Base via x402), which an agent must know before invoking. It stops short of describing error or payment-failure 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?

Two tight sentences with no filler; the resource and returned fields come first, followed by the payment note. 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?

With no output schema, the description helpfully enumerates return fields (time, gas, tx count) and discloses the payment requirement, which is enough to call it correctly. Minor gap: it does not say what happens when the optional block argument is omitted.

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 0%, so the description must carry the burden – and it does, by documenting that the block argument accepts a number or a named tag (latest, safe, finalized). This meaningfully compensates for the empty schema description, though it doesn't state the default when the optional param is omitted.

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: returns a Base block header, and names the returned fields (time, gas, tx count). It is clearly distinguishable from siblings like base_tx or base_receipt, though it does not explicitly name those alternatives.

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?

No guidance on when to use this versus base_tx, base_receipt, or base_gas, and no prerequisites stated. The purpose is inferable from the description but no usage conditions or exclusions are provided.

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?

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuine value beyond them: the return contract (raw result or revert reason), confirmation that no transaction is broadcast, and price/cost ($0.003 USDC via x402), which is non-obvious operational 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?

Purpose is front-loaded, and the three clauses (call semantics, no-tx guarantee, price) each carry distinct information with no filler. Efficient, though the price clause could be considered sidecar metadata.

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?

Return behavior is disclosed despite the absence of an output schema, which is appropriate. However, for a four-parameter tool with 0% schema coverage and no output schema, the omission of any parameter semantics leaves the definition short of complete.

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 0% and the description supplies no meaning for any of the four parameters. 'to' and 'data' are inferable from 'contract call', but 'from' and 'value' are undocumented in both schema and prose, leaving the description unable to compensate for the coverage 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 and resource: 'Simulate a read-only contract call on Base (eth_call)'. This is precise enough for an agent to recognize it as the arbitrary-calldata execution primitive, distinct from read helpers like base_contract or base_balance, though it never names a sibling.

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?

No when-to-use or when-not guidance and no alternative routing. The only contextual hint is 'No transaction sent', which is behavioral rather than selection-oriented, so the agent must infer applicability on its own.

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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context: the tool is paid ($0.003 USDC on Base via x402), which affects invocation. It does not describe return format details, but the pricing disclosure is a valuable addition beyond structured fields.

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 tight sentences, front-loaded with the core question then the capability list, then pricing. No filler; 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?

With no output schema, the description enumerates the key return fields, which is appropriate. It notes pricing and chain context. It could state chain scope for the lookup itself, but it is largely complete for a read-only classification tool.

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 with 0% schema description coverage, so the schema provides only a regex pattern. The description implies the input is an address via 'What is this address?' but does not state format expectations (0x-prefixed 40-hex) or address type restrictions. Adequate for a self-evident single address param, with a clear 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?

It states a specific verb+resource: classify an address as EOA or contract and report code size, proxy implementation, and ERC-20/721/1155 detection. That scope is distinct from siblings like base_balance or base_token, though no sibling is named explicitly. An agent can identify the purpose without opening the schema.

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 explicit when-to-use guidance or routing versus alternatives such as base_token or base_token_risk. Usage is only implied by the enumerated output fields. Exclusions and preconditions are absent.

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?

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds real behavioral context beyond the schema: the output is formatted with symbol and decimals, and each call costs $0.002 USDC via x402, which the agent needs to know before invoking.

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, zero waste, with the core purpose front-loaded and the cost detail trailing. Well structured.

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 usefully notes return formatting (symbol and decimals) and pricing. For a two-parameter read tool this is nearly complete; only the token-vs-address distinction on inputs is left implicit.

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 0%, so the description carries the burden. It clarifies that the balance is for a wallet ('address') holding a specific token, but does not explain that 'token' is an ERC-20 contract address matching a 0x-pattern. Names are largely self-explanatory, so this is only a minor 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: the ERC-20 token balance of a Base wallet. This clearly distinguishes it from the native-coin sibling base_balance, though it never names that sibling explicitly.

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?

Usage is only implied by the purpose; there is no explicit when-to-use, no when-not, and no routing to alternatives like base_balance (native) or base_portfolio. A capable agent can infer it, but nothing is stated.

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?

Annotations declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds genuinely new behavioral context by disclosing a paid endpoint ($0.002 USDC on Base via x402), which an agent must know before invoking. It still omits whether estimation can fail or how the quote is priced, but the cost disclosure is real added value beyond the annotations.

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, zero waste, with the core action front-loaded and the pricing note trailing. Every sentence 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?

For a 4-parameter tool with no output schema and 0% schema description coverage, the description should at minimum clarify the transaction inputs it estimates for. It covers purpose and payment model but leaves parameter meaning and the shape of the estimate unexplained; annotations only partially fill the gap.

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 0% and the description never mentions 'to', 'from', 'data', or 'value'. It cannot compensate for the gap: an agent gets no meaning for the required 'to'/'from' fields or the optional calldata/value fields beyond their type patterns.

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 ('Estimate gas and the USD cost of a Base transaction') with a clear scope qualifier ('before signing it'). It implicitly differentiates from the sibling base_gas by adding the USD cost dimension, but never names or contrasts with that sibling, so differentiation is left to inference.

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?

'before signing it' gives a rough usage context, implying pre-transaction estimation. However it does not say when to prefer this over base_gas or base_call, nor does it state prerequisites or exclusions. Usage is implied rather than stated.

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?

Annotations declare readOnlyHint=true and openWorldHint=true, so the agent knows this is a safe, external read operation. The description adds the paid-access detail ($0.001 USDC on Base via x402), which is useful context beyond annotations. However, it does not describe the return format or whether the call incurs the cost each time.

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 core purpose followed by the cost model. No wasted words.

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?

The description covers the tool's purpose and pricing but lacks detail on return format, frequency of updates, or error conditions. Given the simplicity (no params, no output schema) and the presence of annotations, it is minimally adequate but not fully complete.

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 tool takes no parameters, so the baseline is 4. The description does not need to document any parameters, and it correctly avoids discussing them.

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 resource (Base gas) and enumerates the specific data points: base fee, suggested priority fee, and max fee per gas. It does not explicitly distinguish itself from sibling tool base_estimate_gas, which is a gap, but the specific enumeration of gas metrics gives a clear 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?

No guidance on when to use this tool versus alternatives like base_estimate_gas or when it should be preferred. It only mentions the pricing model (x402) but does not indicate when an agent should invoke 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?

Annotations already cover readOnlyHint and openWorldHint, and the description adds genuinely new behavior: multi-source resolution (IPFS, Arweave, data URIs, https) and the concrete cost ($0.005 USDC via x402). It stops short of explaining the x402 payment/auth flow the agent must 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, zero filler, with the core resource stated first and the cost constraint appended. 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?

With no output schema, the description still conveys what is returned (metadata), where it is resolved from, and the micro-payment model, which is roughly what an agent needs. The unresolved x402 payment mechanics are the main remaining gap for a paid, open-world read.

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 0%, so the description carries the burden for the two required parameters, yet it says nothing about contract vs tokenId beyond implying an ERC-721/1155 identity. The schema's regex patterns help validation but add no semantic 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?

States a specific resource (NFT metadata for an ERC-721/1155 token) and chain (Base), which cleanly separates it from the sibling base_nft_owner even though no sibling is named. The verb is implied by the noun phrase rather than stated, keeping it 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?

No when-to-use guidance, prerequisites, or alternative routing is provided. It never tells the agent to prefer base_nft_owner for ownership checks or when metadata lookup is the wrong call.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description contributes the useful non-annotation fact that calls cost $0.002 USDC via x402, but says nothing about failure modes (nonexistent token/contract) or the return value.

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 core purpose; the pricing sentence is short and genuinely relevant to invocation via x402. No filler, though the price note could be consolidated.

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 two-parameter read tool with no output schema, the description is minimally adequate: purpose and cost are covered, but parameter meaning, return shape, and error behavior are absent. Annotations cover only the read-only safety profile.

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 0% for two required parameters, so the description carries the full burden and does not mention 'contract' or 'tokenId' at all. The schema patterns imply format constraints, but the description adds nothing about address format, token ID type, or chain selection.

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 resource and result ('Current owner of an ERC-721 token on Base'), which lets an agent distinguish it from sibling base_nft_metadata or base_token. It is clear but does not explicitly name the sibling it differs from.

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?

No when-to-use guidance, no prerequisites, and no mention of alternative tools such as base_nft_metadata for token attributes. The agent must infer usage entirely from the name and 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?

Annotations already cover safety (readOnlyHint=true, openWorldHint=true), but the description adds a critical behavioral fact: the call costs $0.004 USDC on Base via x402. That payment requirement is exactly the kind of non-obvious trait structured fields don't convey. It doesn't mention failure modes for unpaid calls or rate 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?

Two short sentences with zero waste, front-loading what the tool returns before the pricing detail. Nothing redundant, though the price sentence could be slightly more informative about the payment flow.

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 does describe the shape of results (token holdings with USD values), which is helpful. However, for a paid tool it omits how the x402 payment is made, what an unpaid call returns, and whether custom token lists change the price — gaps that matter for correct invocation.

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 0%, so the description carries the burden. It does clarify the tokens parameter semantics: default is 'ETH plus major tokens' or 'up to 20 you choose', which matches maxItems=20. The address parameter is left unstated, but its meaning is evident from the name and pattern.

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 resource and scope: a wallet portfolio snapshot on Base covering ETH plus major tokens with live USD valuation. This clearly separates it from siblings like base_balance or base_erc20_balance (single-asset reads), though no sibling is named explicitly.

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?

No guidance on when to pick this over base_balance, base_erc20_balance, or base_token — the agent must infer portfolio-level vs single-token intent. The price note hints at a paid path but doesn't say when that cost is worth paying or what happens if payment is absent.

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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds venue sourcing and a meaningful operational trait: the x402 payment cost of $0.003 USDC on Base. Auth, return, and pagination details are still absent, but the added cost disclosure is valuable.

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 the core capability front-loaded and no wasted wording. The payment sentence is terse and useful, though 'Price' is slightly ambiguous because it could be read as the token price rather than the tool's cost.

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 one-parameter tool with annotations and no output schema, the description covers the returned data and cost. However, it leaves the required token address format implicit and does not describe the return shape, which are meaningful gaps for an agent trying 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 description coverage is 0%, and the single token parameter has only a regex pattern, no textual description. The description says 'any Base token' but does not clarify that the input must be a 0x contract address or explain the required parameter, so it fails to compensate for the low 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?

States specific data provided (live USD price and liquidity) and the sources (Uniswap v2/v3 and Aerodrome pools), identifying the resource as any Base token. It does not explicitly differentiate itself from siblings like base_token or base_portfolio, so it is clear but not sibling-routing precise.

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?

No explicit when-to-use, when-not-to-use, or alternative tool guidance is given. The phrase 'any Base token' implies context, but the agent must infer when to choose this over base_token, base_token_risk, or base_portfolio.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description usefully adds the x402 payment model and the $0.003 USDC cost, which is genuinely behavioral context beyond the annotations, but says nothing about response shape, error cases, or what a failed/missing receipt looks like.

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 tight sentences, contents first and pricing second. The pricing sentence earns its place because it signals a paid (x402) call, though it could have been placed after explicit usage routing.

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 single-parameter paid read tool with no output schema, the description covers what is returned and what it costs, which is the minimum an agent needs. It stops short of routing guidance versus siblings and of any note on the payment/x402 invocation flow.

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 0% and the single parameter `hash` is undocumented in both schema and description. The phrase 'transaction receipt' weakly implies this is a transaction hash, but no format, required-ness, or semantics are added beyond the regex pattern.

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 — a Base transaction receipt — and enumerates its contents (status, gas, decoded ERC-20 Transfer events). However, it never distinguishes itself from the adjacent base_tx sibling, leaving the agent to infer whether to fetch the receipt or the transaction.

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?

No when-to-use guidance and no named alternative. The agent is told what the tool returns but not when to prefer it over base_tx, base_transfers, or base_call, which is a real ambiguity given the sibling list.

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?

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely new context by disclosing the paid access model ($0.002 USDC on Base via x402), which is behaviorally important, but it says nothing about failure modes (e.g., non-ERC-20 addresses) or how the payment flow is triggered.

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 compact sentences with zero filler, and the returned fields are front-loaded before the payment note. Every sentence carries information the agent needs.

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 competently compensates by listing the return fields, and it flags the paid access model. Remaining gaps are minor: it does not say what happens for non-ERC-20 or wrong-chain inputs, but for a single-address read tool this is close to complete.

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 0% for the single 'token' parameter, whose only documentation is a hex-address regex. The description's mention of 'ERC-20 metadata' loosely implies the parameter is an ERC-20 token address, adding marginal meaning, but it never states this explicitly.

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 the resource (ERC-20 metadata on Base) and enumerates the exact fields returned (name, symbol, decimals, total supply), which clearly separates it from siblings like base_erc20_balance, base_price, and base_token_risk. It lacks an explicit verb, but the purpose is 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?

There is no guidance on when to use this tool versus alternatives such as base_erc20_balance (balances) or base_price (pricing), nor any prerequisites or exclusions. The agent must infer usage entirely from the field list and sibling names.

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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is partly covered, but the description adds meaningful context the annotations lack: the simulation is a 'real buy/sell eth_call', the verdict scale is low/caution/high/avoid with evidence, and the tool requires a $0.01 USDC payment via x402. That payment requirement is a genuinely useful behavioral 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?

Dense and front-loaded: the verdict purpose comes first, the evidence sources second, the return scale third, and the cost last. Every sentence carries information, though packing five distinct checks plus payment terms into three sentences is near the density limit.

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, but the description compensates by naming the return verdict categories and the evidence basis, and it discloses the payment model. An agent can call this and interpret the result without further documentation; only pricing mechanics/error behavior are left implicit.

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 (token, simulate) are fully documented in the schema. The description's mention of buy/sell simulation clarifies intent behind the 'simulate' flag but adds no format or syntax detail beyond the schema. 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?

States a specific verb+resource (risk verdict for a Base token) and enumerates the exact checks performed: honeypot/tax simulation, mint/blacklist/pause/fee powers, proxy upgradeability, ownership, DEX liquidity. This clearly distinguishes it from the generic sibling base_token and from base_contract.

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 'for trading agents' implies the intended context, and the enumeration of checks hints at when it matters (pre-trade due diligence). However, no alternatives are named (e.g., use base_token for metadata or base_contract for raw bytecode) and there is no explicit when-not 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?

The description adds genuinely useful behavior beyond the readOnlyHint/openWorldHint annotations: hard caps of 2,000 blocks and 100 results, plus a $0.005 USDC x402 payment requirement. It stops short of explaining truncation semantics, default lookback when blocks is omitted, or retry/auth behavior for the paid call.

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, zero filler, with the scope and filters front-loaded and the cost/limit caveat last. Every clause carries information the agent needs.

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 3-param, zero-required, paid, no-output-schema tool, the definition covers limits and pricing but leaves notable gaps: behavior when no filters are given, default block window, result ordering/pagination, and how to actually satisfy the x402 payment. Adequate but not complete.

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?

With 0% schema description coverage the description must carry parameter meaning, and it partially does: 'token and/or wallet' maps to the token/address params and 'up to 2,000 blocks' maps to blocks. It does not define the block semantics (lookback vs. range), the default used when blocks is absent, or how token and address combine when both are supplied.

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 (list) and resource (recent ERC-20 Transfer events on Base) with clear filter dimensions (token and/or wallet). It is distinguishable from siblings like base_tx or base_erc20_balance, but never names or contrasts with an alternative, so sibling routing is left to inference.

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?

Usage is implied by the filter phrasing 'for a token and/or wallet,' telling the agent what inputs select this data. There is no explicit when-to-use versus base_tx / base_receipt, no statement about what happens when both filters are omitted, and no exclusions.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds real value beyond them: it discloses a per-call price ($0.003 USDC on Base via x402) and lists the returned fields in lieu of a missing output schema. It stops short of describing rate limits or error behavior, but the pricing disclosure is strong 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?

Two compact sentences, front-loaded with purpose and returned fields before the pricing note. Every clause earns its place 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 single-argument read-only lookup with no output schema, the description adequately compensates by enumerating return fields and disclosing the x402 cost. The main omission is sibling differentiation against base_receipt/base_call when the agent is choosing between them.

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?

With 0% schema description coverage, the description says only 'by hash' — it does not explain that the hash is a 32-byte transaction hash or add format guidance. The schema's pattern (^0x[0-9a-fA-F]{64}$) does carry the format constraint, so the gap is partially covered, but the description itself adds little beyond naming the input.

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 ('Base transaction details by hash') and enumerates the fields returned (from, to, value, calldata selector, block, status), so the agent knows exactly what this retrieves. However, it does not differentiate itself from sibling base_receipt or base_call, which are close in scope and could confuse selection.

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 explicit when-to-use guidance, no mention of alternatives, and no prerequisites stated. The agent must infer it should use this for transaction lookups versus base_receipt, base_call, or base_transfers purely from the name and field list.

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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds two material traits the annotations don't: determinism (reproducible output for identical inputs) and a concrete cost/payment rail ($0.25 USDC on Base via x402), which is critical for an agent deciding whether to call it. It still omits what happens on payment failure or how long scoring takes.

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 tight sentences with no filler, and the core purpose is front-loaded ahead of the cost note. It is efficient, though the extreme brevity contributes to the gaps in other dimensions.

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 four parameters, 0% schema descriptions, and no output schema, the description should compensate for input semantics and expected result. It supplies only the payment model, leaving the agent unable to construct a valid, meaningful call from the description alone.

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 0%, so the description carries the full burden and largely fails it. 'seven-pillar' loosely hints at the pillars array (maxItems 7), but opportunityName, stage, and redFlagIndices are entirely unexplained, including what the red-flag indices refer to and how many pillars are expected.

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?

It names a specific resource and result ('opportunity score') and a distinguishing trait ('seven-pillar', 'deterministic'), but 'score' is used as a noun without a clear verb, and neither 'opportunity' nor 'pillar' is defined. An agent can't tell from this alone what domain the opportunity belongs to or what the score represents. It does separate itself from the base_* and audit_* siblings, which matters.

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 only guidance is a price tag; there is no statement of when to use this tool versus siblings, what input is required, or what preconditions exist beyond paying. The payment note is a precondition, not usage routing, so the agent is left to infer everything about selection.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely useful behavioral context the annotations cannot: a $0.50 USDC charge on Base via x402, i.e. a paid call. It still omits what the triage returns and whether payment is per-call or per-invoice.

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, zero filler, with the core purpose front-loaded before the pricing clause. Nothing could be cut without losing information.

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 carries the burden of explaining what the triage returns (aging buckets, recommended actions) and it does not. Combined with four undocumented required parameters, an agent cannot predict the result shape or input semantics.

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 0% and all four parameters are required and undocumented. The description adds nothing about invoiceNumber, clientReference, amount, or daysOverdue – notably the odd negative-minimum daysOverdue (-365) is left unexplained, so the description fails to compensate for the coverage 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: 'invoice aging and next-action triage', qualified as deterministic. None of the siblings (base_*, audit_*) overlap with invoice triage, so differentiation is implicit rather than stated. 'Next-action triage' remains somewhat vague about what advice is produced, keeping it 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?

No when-to-use context, no prerequisites, and no alternative named despite 21 sibling tools. The only guidance is the payment term, which is not usage guidance.

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