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

With no annotations, the description carries the full behavioral burden. It adds useful context by stating the tool is free and listing what it returns, which implies a read-only discovery operation, but it does not explicitly disclose side effects, authentication requirements, rate limits, response size, or output format.

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?

It is a single front-loaded sentence that identifies the tool as free discovery and enumerates the returned artifacts without unnecessary wording. Every phrase contributes to explaining what the tool is and what it provides.

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 zero-parameter read-only catalog with no output schema, the description names the key returned artifacts and states that it is free. It could be slightly more complete about response structure or size, but it gives enough information to invoke the tool 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?

The tool has zero parameters and an empty input schema, so there are no parameter meanings for the description to clarify. The baseline for zero parameters is 4, and the description does not need to compensate for any schema gaps.

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 ('returns') and resource (the Coinbase x402 Bazaar semantic catalog, available verification endpoints, pricing in Base USDC, and schema definitions). It labels itself a discovery tool, which helps distinguish it from the sibling verify_* tools, but it does not explicitly name or contrast those siblings.

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

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

The phrase 'Free discovery tool' implies it is used to discover endpoints, pricing, and schemas rather than to perform verification, and the sibling names suggest that verification belongs to the other tools. However, it provides no explicit when-to-use, when-not-to-use, or named alternative guidance.

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

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

With no annotations, the description carries the full behavioral burden, and it does deliver one genuinely important fact: the tool is paid at 50000 Base USDC atomic units, which is critical pre-invocation context. It omits the rest of the safety/behavior profile — what a failed equivalence means, whether payment is consumed on failure, how fuzzing affects runtime, and what payment mechanism the paymentHeader feeds into.

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?

A single compact sentence with the price front-loaded and the operation stated second — no filler or repetition. The density is appropriate, though the terse phrasing makes 'consensus' and 'boundary grids' harder to parse than necessary.

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?

This is an 8-parameter, paid, computationally heavy verification tool with no annotations and no output schema, so the description must explain the verdict semantics and payment flow itself. It supplies neither, leaving the agent unable to predict the return value, failure behavior, or how the required code_a/code_b comparison is actually executed.

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 50%, which sits at the baseline threshold. The description names code_a and code_b and the 'boundary grids' concept that maps onto domain_bounds, adding a little meaning beyond the schema's terse property descriptions, but seed, fuzz_iterations, unsigned_bit_width, and paymentHeader get no explanation of effects on verification rigor or cost.

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 operation — 'formal differential consensus equivalence verification between code_a and code_b across boundary grids' — which is far more informative than the bare tool name and tells the agent it compares two implementations for semantic equivalence. It does not, however, distinguish this from the sibling x402_verify_vault_rounding / x402_verify_polymarket_basket / x402_verify_zk_or_bitvec verifiers, so the agent must infer the domain from the parameter names.

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 statement, no condition that selects this tool over the sibling verifiers, and no statement of prerequisites beyond the parenthetical price. The agent can infer that it is used when comparing a reference and candidate implementation, but nothing in the text confirms or excludes any scenario.

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

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the price of 20000 Base USDC atomic, and the verification framing implies a computational/read-only operation, but it does not explicitly state read-only status, side effects, permissions, or return 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?

The description is a single front-loaded sentence with no wasted wording. Payment cost and domain purpose are both stated 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?

For a paid tool with seven parameters, no annotations, no output schema, and low schema description coverage, the description is too thin. It identifies the domain but leaves out usage guidance, parameter meaning, and behavioral details an agent would need to invoke it confidently.

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 only 29%, so the description should compensate for the undocumented parameters, but it provides no explanation of fee_bps, payout_per_share, convert_no_subset_size, or custom_conversion_formula. The domain terms loosely relate to the basket inputs but do not add practical parameter semantics.

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

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

The description names a specific verification domain: Polymarket NegRisk / Conditional Token solvency and Dutch-book net edge. That distinguishes it from sibling verification tools such as vault rounding or ZK/bitvec verification, although it phrases the action as a noun phrase rather than an explicit verb.

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 states that the tool is paid but gives no guidance on when to use it versus the sibling verification tools. It does not mention prerequisites, when-not-to-use cases, or how the required basket inputs should be prepared.

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

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

With no annotations, the description carries the full disclosure burden, and it does add one valuable fact: this is a paid tool costing 20000 Base USDC atomic units, plus that verification is formal (Z3). It omits critical behavior – whether payment failure blocks execution, whether the operation is read-only, how long verification takes, and whether the tool ever mutates anything.

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?

A single tight sentence with the cost front-loaded and the subject matter immediately following. No filler or redundant restatement of the name, though it is arguably too terse for the tool's complexity.

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 paid formal-verification tool with no output schema and no annotations, the definition leaves the agent uncertain about the shape of the result (verdict? counterexample?), payment-failure behavior, and the semantics of the bound parameters. The price disclosure and named vulnerability classes cover the essentials of what the tool does but not enough to call it confidently.

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 only 50%: max_assets, max_shares, and check_zero_share_mint have no schema descriptions, and the description does not explain that they act as search bounds or that check_zero_share_mint toggles the zero-share inflation check it names. Only the zero-share vulnerability mention loosely hints at one undocumented 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?

The description names a specific verb and resource ('Formal Z3 verification of vault share rounding') and scopes it to ERC-4626 / Euler / Meteora plus class of vulnerability (donation attacks, zero-share inflation). That makes it clearly distinguishable from the sibling verifiers (polymarket basket, zk_or_bitvec, differential_spec) by topic, though it never explicitly contrasts itself with 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?

There is no statement of when to call this versus the other x402_verify_* tools, no prerequisites beyond price, and no guidance on the required Python/AST inputs being valid preview_deposit/preview_redeem definitions. The agent must infer usage entirely from the topic sentence.

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 are absent, so the description carries the full burden. It does disclose the paid nature and exact price (30000 Base USDC atomic), which is valuable, but says nothing about what a verification result looks like, what happens when verification fails, how payment is rejected, or runtime/duration expectations. No output schema exists to fill that gap.

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?

A single dense sentence with the price front-loaded and no filler, though the heavy parentheticals compress the two modes into something harder to parse than a short bulleted structure would be.

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 30% schema coverage, nested objects, no annotations, and no output schema, one sentence cannot be sufficient. An agent has no way to know which parameters are required per mode, what the return value contains, or what payment failure looks like.

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 only 30% across 10 parameters. The description hints that witness_vars/public_inputs/preconditions/constraints_exprs belong to zk mode and expr/var_bitwidths/target_bitwidth belong to bitvec mode, but never states this mapping, and leaves output_var and paymentHeader wholly unexplained.

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 ('Formal Z3 verification') and names the two distinct capabilities (ZK circuit witness uniqueness/soundness vs BitVector integer cast truncation), which lets an agent tell it apart from the rounding/differential siblings. Lacks an explicit cross-reference to siblings, so not 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 guidance on when to pick this tool over x402_verify_vault_rounding or x402_verify_differential_spec, nor any guidance on how to choose between the two modes. The mode enum exists in the schema but the description never says which parameter set belongs to which mode.

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