BIG Machine Market

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

The readOnlyHint and openWorldHint annotations already cover the safety profile, yet the description adds substantive behavior: per-execution cost, no-subscription model, the flag that gates paid execution, a binary 0/1 paid result, and abstention-without-billing for undecidable inputs. It does not disclose auth or rate limits, but that is above the annotation-covered baseline.

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 purpose statement is buried fourth of five sentences behind marketplace boilerplate ('Machine-native checks from $0.001', 'No subscription required', 'Browse the $0.001 primitive catalog'), and the catalog-browsing sentence does little to help select or invoke this specific tool. Front-loading is poor and at least one sentence does not earn 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?

An output schema exists, so return values need not be explained, and the annotations cover safety. Given a 2-param read/prepare tool, the description supplies purpose, billing/gating behavior, and result nature, leaving only cross-sibling routing and param formatting unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it partially does by mapping the two params: 'the original human message' (HUMAN_MESSAGE) and 'an agent's current interpretation' (CURRENT_INTERPRETATION). It gives no format, length, or encoding guidance, so it fills only half the gap left by the empty schema.

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 contains a specific verb+resource: it 'checks whether an agent's current interpretation materially differs from the original human message.' That is unambiguous and separable from the sibling prepare_state_deviation_purchase. However, it never references that sibling or draws the contrast, so differentiation rests entirely on the tool name.

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 real flow guidance: create a purchase intent and pay only when /market.primitive_entry.paid_execution_enabled is true, otherwise paid execution is unavailable. That is a useful precondition, but there is no explicit 'use this vs prepare_state_deviation_purchase' routing or when-not-to-use guidance beyond the payment gate.

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?

Beyond the readOnly/openWorld annotations, it discloses genuinely useful behavior: the paid result is binary 0/1, undecidable inputs abstain before billing (i.e., no charge on abstention), and payment is gated on a market flag. That billing/abstention detail is exactly the kind of trait annotations cannot express. It does not cover latency, retries, or what 'prepare' returns as a machine-payable artifact, hence not a 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?

Four sentences, and the first ('Browse the $0.001 primitive catalog') is marketing filler that does not help an agent invoke the tool. The actual purpose arrives in sentence three, so the description is not front-loaded. The remaining sentences are dense and earn their 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?

An output schema exists, so return-shape explanation is not required, and the description still adds the salient output fact (binary 0/1 with abstention). Payment gating, abstention-before-billing, and the core comparison are all covered. Only the parameter format conventions remain missing for 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 description coverage is 0%, so the two required parameters EXPECTED_STATE and OBSERVED_STATE are entirely undocumented in the schema. The description maps them conceptually ('observed state materially differs from an expected state'), which is the only semantic signal available, but it never specifies accepted formats (raw text, JSON, structured state) or how 'materially' is judged. Partial compensation only.

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 third sentence gives a concrete verb+resource: 'Prepare a machine-payable x402 request that checks whether an observed state materially differs from an expected state.' That is enough to distinguish it from the similarly named sibling prepare_interpretation_delta_purchase by concept, though the description never explicitly contrasts them. The opening catalog/billing sentences dilute but do not obscure the core 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?

It states a real precondition for charging ('pay only when /market.primitive_entry.paid_execution_enabled is true; otherwise paid execution is unavailable'), which is useful operational context. However, it gives no guidance on when to choose this tool over prepare_interpretation_delta_purchase or what input qualifies as a deviation check. Usage is implied rather than instructed.

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