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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states 'Read-only,' which is a critical safety trait. It also describes the scope of checks and mentions 'graded risk level,' hinting at output structure. However, it omits details like network call behavior or error handling, which are minor for a read-only tool, justifying a 4.

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, well-structured sentence that front-loads the core action ('Lists standing approvals') and then efficiently details the scope and output. The opening rhetorical question adds a human touch without bloat, and every phrase contributes to understanding, earning a top score for conciseness.

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

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

For a tool with one parameter and no output schema, the description covers the main functional aspects: what it lists, across which chains, and the graded risk element. It does not specify the exact return format (e.g., array structure), but the nature of 'lists' implies a collection, and the description is sufficient for an agent to infer expected behavior. A 4 reflects slight incompleteness in output detail.

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 input schema already provides a complete description of the 'address' parameter (100% coverage), specifying the accepted formats (EVM 0x…, TRON T…, Solana base58). The description does not add any additional semantic meaning beyond what the schema states, so it relies on the schema, matching the baseline score of 3.

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 with a specific verb ('lists') and resource ('standing approvals'), enumerating the covered chains (EVM, TRON, Solana) and approval types (ERC-20 allowances, NFT operator approvals, Permit2 grants). This distinguishes it from the sibling check_token, which presumably focuses on token data, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context about what the tool does but does not explicitly contrast it with check_token or state when to prefer one over the other. It implies usage through its detailed scope, but lacks explicit 'use this when' or 'not for' exclusions, placing it at a 4 rather than 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?

With no annotations, the description carries the behavioral burden and does most of the work: it discloses that the tool simulates a swap, which risk classes it surfaces, and that it returns safe/warn/block with evidence. It falls short of an explicit statement that no real transaction or state change occurs, leaving slight ambiguity about whether funds are moved.

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?

Five short sentences front-load the main purpose and each adds necessary detail: method, risks detected, second check, output, and call timing. There is no filler or repetition.

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

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

For a simple 2-parameter tool with no output schema, it covers what the tool does, how it works, what it returns, and when to call it. Minor gaps remain around exact evidence shape and whether the simulation is entirely read-only, but these do not block 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 description coverage is 100% and both parameters are already documented with chain options and address formats. The description adds no new parameter-level meaning beyond referring to the token contract, 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 names a concrete purpose ('pre-trade safety check'), a distinctive method (simulated buy-and-sell against live liquidity), and secondary checks (ticker impersonation). It clearly differentiates from the sibling check_approvals, which concerns approvals, by focusing on token tradability and honeypot/tax risks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says 'Call BEFORE buying', giving a clear temporal/contextual trigger. It does not explicitly state when to prefer check_approvals or exclude cases, but the pre-trade context makes the intended use obvious.

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

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses that nothing is signed, sent, or broadcast, that the amount is hard-coded to zero, that it runs against live state in the same simulated block, and that it is read-only. This fully compensates for the missing annotation layer.

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 and front-loaded, with the core purpose in the first sentence. Minor redundancy exists: 'Read-only.' repeats the earlier 'Nothing is signed, sent or broadcast', so a small deduction is warranted, but every other 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?

The definition covers purpose, workflow, safety, and parameter interplay well, and the schema covers all parameter semantics. However, there is no output schema and the description only says 'the calldata comes back' without specifying the return shape or how simulation failure is reported, leaving a modest 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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by explaining the concrete transactions behind kind values ('approve(spender, 0)', 'setApprovalForAll(operator, false)', Permit2) and by stating the amount is hard-coded to zero, which tells the agent no amount parameter is needed.

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 opens with a specific verb and resource: 'Prove a revoke BEFORE it is signed' and then details exactly which approvals it builds (ERC-20, NFT operator, Permit2). It also differentiates itself from siblings by positioning check_approvals as the discovery step and simulate_revoke as the proof step.

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?

Explicit workflow guidance is provided: 'Use check_approvals first to find which grant to remove; use this to prove that removing it will actually work.' It also clarifies the Permit2 case where a different kind must be chosen, and states the read-only, nothing-broadcast constraint that frames 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.