presign-guard

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

Despite readOnlyHint and openWorldHint annotations, the description adds meaningful behavioral context: the $0.01 USDC fee via x402, the types of submitted payloads, the color-coded verdicts, and the specific risk factors checked. This goes well beyond the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-structured: cost and timing are front-loaded, the input and output are stated concretely, and the safe-action policy is explicit. The closing 'Same as POST /v1/check' is a useful pointer without adding bloat.

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 still explains what the agent will receive: green/orange/red with reason codes covering spender flags, sanctions, allowances, and token risks. It also covers cost, when to call, and how to act on results, making it complete for an agent to use 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 baseline is 3. The description reinforces which payload types map to which parameters and gives examples like Permit2 and Seaport, but most parameter meaning already lives in the schema. It adds moderate context but does not carry the semantic burden.

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 identifies a specific action: a pre-sign risk check that evaluates transactions, approvals, and signatures and returns green/orange/red with reason codes. It does not explicitly differentiate itself from siblings like presign_quick_check, but the resource and behavior are unmistakable.

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 strong when-to-use guidance: call before signing, proceed only on green, ask the user on orange, and never sign on red. It does not explicitly contrast with sibling tools or state when to choose a quick check instead, so it stops short of a 5.

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

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

Annotations already declare readOnlyHint=true, so the description correctly avoids restating that. It adds meaningful behavioral details: the $0.03 USDC cost via x402 on Base, and the 3-5 sentence explanation length. It also references the POST /v1/check/explain endpoint for clarity. No contradictions with 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?

The description is two sentences with no redundancy. It front-loads the key differentiator (explanation) and the cost, then clarifies it matches presign_check's verdict/reason codes. Every sentence earns its place, making it highly efficient.

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 11 parameters, the schema handles parameter semantics well. The description covers the purpose, cost, output content (verdict/reason codes plus explanation), language options, and references an endpoint. It doesn't detail the exact response structure, but no output schema exists, and the mention of 'verdict and reason codes' is sufficient for an agent to understand the expected outcome.

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 every parameter. The description adds only marginal value, such as indicating the lang parameter is for the explanation language, which is already in the schema. It does not provide additional syntax or format details beyond the schema, so the baseline of 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 the tool's function: a pre-sign risk check that returns the same verdict and reason codes as presign_check, but adds a plain-language explanation. This explicitly distinguishes it from its primary sibling, presign_check, by the added feature. The verb and resource are specific, and the tool's 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?

The description implies usage when a human-readable explanation is needed by contrasting with presign_check ('same as presign_check, plus explanation'). It also mentions the cost, which is a practical consideration. However, it does not explicitly mention when not to use it or alternative tools like presign_quick_check or token_verdict, leaving some room for interpretation.

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 known. The description adds useful operational context: it is free, rate-limited to 10 calls per hour, and returns only the quick verdict with no details. This goes beyond the annotations without contradicting them.

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 that front-load the free verdict, define the scope, state the rate limit, and route to alternatives. Every sentence adds useful information with 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 10-parameter tool with no output schema, the description still provides enough context: it defines the return as a color verdict, explains the rate limit, and names the more detailed sibling tools. The schema handles parameter semantics, and the annotations handle safety. Nothing essential 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?

The schema covers 100% of the 10 parameters with clear type-conditional descriptions, so the baseline applies. The description's mention of transaction, approval, or signature maps to the type enum but adds no new parameter-level meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific outcome—green/orange/red verdict—for the concrete resources: transaction, token approval, or EIP-712 signature. It also distinguishes itself from the presign_check siblings by saying it is the free 'verdict only' variant. This makes the tool's 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?

The description explicitly names the alternatives presign_check and presign_check_explain and the conditions for choosing them: need reason codes and details, or plain-language explanation. It also gives the 10-calls-per-hour limit, which informs when the paid siblings should be used.

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 indicate read-only and open-world behavior; the description adds a concrete rate limit and clearly states the output is only the verdict/grade, excluding reasons, summary, and market data. It does not contradict annotations, though it leaves minor details like rate-limit failure behavior unstated.

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 and front-loaded: it starts with the free verdict/grade output, then rate-limit, then the alternative for richer data. Every sentence earns its place with 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-only tool, the description covers output semantics, supported token families, rate limits, and the richer paid alternative. Even without an output schema, an agent can correctly decide to call it and interpret the returned verdict/grade.

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 chain and address are already documented with formats and examples. The description only echoes 'Solana or EVM token' and adds no real parameter-level information beyond what the schema provides.

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 operation: return a green/orange/red verdict and grade for a Solana or EVM token. It also names the output scope with 'only' and explicitly contrasts with token_verdict, making the tool distinguishable from 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?

Tells the agent when to use this free quick version and when not to: for reasons, summary, or market data it routes to token_verdict ($0.01). It also warns about the shared 10-calls-per-hour limit with presign_quick_check, giving clear capacity-aware 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description adds value by disclosing the $0.01 USDC cost via x402, the supported chains, and the full set of returned verdict fields. It does not contradict the annotations and adds meaningful context beyond them.

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 dense sentence that front-loads the paid nature and use case, then efficiently enumerates inputs, outputs, and reason codes. Every clause earns its place, and the 'Same as GET /v1/token' pointer is useful. It is long but not bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description fully enumerates the return payload: verdict color, grade, reason codes, summary, and market data. It also states cost, chains, and input requirements. It is incomplete only regarding error cases and edge behavior, but it is otherwise strong for a two-parameter 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 100%: both parameters are already documented with chain enum and address format. The description restates the chain list and the address/mint concept but adds no new semantic detail beyond what the schema already provides, so the baseline score 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?

The description clearly identifies a specific action ('call this before your agent buys, holds or accepts a token') and a specific resource (token risk verdict). It lists the exact outputs. However, it does not explicitly differentiate itself from the sibling tool token_quick_verdict, so it misses the top score.

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 clear when-to-use context: before buying, holding, or accepting a token. It also spells out required inputs. It does not provide when-not-to-use guidance or name alternatives, so it falls short of explicit exclusion 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds meaningful behavioral context: the cost ($0.02 USDC via x402), the payment rails (Base or Solana), the output categories (green/orange/red, grade, one-line summary, every ERC-20 allowance with spender), and the actionable revoke.cash link. It also discloses the limitation that NFT approvals are not covered. This goes well 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?

The description is dense but well-organized: cost and payment method are front-loaded, then the output details, then the exclusion. Every sentence adds information. It is slightly long but justified by the richness of the tool's output and the paid nature of the call. The 'Same as GET /v1/approvals' line is a useful compact reference.

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 audit tool with two fully documented parameters and no output schema, the description covers the key things an agent needs: what it costs, what chains it supports, what the output looks like, and what it does not cover. It does not describe pagination or rate limits, but for a simple audit call with a defined output shape, this is a minor 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 100%, so the schema already documents both parameters ('EVM chain to audit' and 'Wallet address (0x...)'). The description adds the chain list and the wallet use case, but it doesn't add deeper parameter semantics such as address format validation or chain-specific nuances. Baseline 3 is appropriate when the schema carries the full parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('audit'), a specific resource ('open token approvals of an EVM wallet'), and the exact chains supported. It also explicitly excludes NFT approvals, which distinguishes it from any sibling that might cover broader approval types. The 'Same as GET /v1/approvals' line further anchors the tool's identity.

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 concrete use case ('for example your agent's own wallet as a periodic check') and states what is not covered ('NFT approvals are not covered'). It does not explicitly name sibling tools or say when to prefer an alternative, but the use case and exclusion provide clear context for when this tool is appropriate.

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