Motor Soberano (pay-per-call, x402)

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses passive page loading like a visitor, no login or security testing, no storage, charge-on-success only, and a $0.50 per-call x402 price. These are exactly the side-effect, cost, and data-handling details an agent needs.

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 front-loaded with the core action, and every clause appears to earn its place by covering scope, output, limitations, cost, and storage. It is a single long sentence with a closing price note, which is efficient though slightly harder to scan.

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 one-parameter audit tool with no output schema, the description is complete: it explains what the audit returns (scores, failing audits, base64 PDF), what it does not do, and the charging/storage model. Nothing critical for correct invocation appears to be 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?

Schema coverage is 100%, so the single `url` parameter is already fully documented in the schema. The description adds useful scope around what URLs are acceptable (public, Shopify storefronts) and the audit context, but it does not add syntax or format details beyond the schema’s example.

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 tool action and resource: an automated Lighthouse audit of public websites or Shopify storefronts, and enumerates the exact outputs (Performance, Accessibility, Best Practices, SEO scores, failing audits, PDF report). It is immediately distinguishable from the unrelated sibling tools.

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 clearly defines the target scope (public website or Shopify storefront) and exclusions (no login, no security testing), plus runtime shape (mobile emulation, single run). It does not explicitly name alternatives, but the sibling tools are unrelated, so this is strong contextual 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 burden and largely meets it: it discloses the 1024 output-token ceiling, ~50 tokens/s throughput, that prompts and answers are not stored, and the billing model (pay per request, charged only on success, $0.002 x402). It omits failure modes beyond billing, how the 40-message cap is enforced, and any auth/payment handshake details.

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?

Six compact clauses, front-loaded with identity and model before cost and privacy details; every sentence carries operational information. The marketing-flavoured parenthetical '(Apache-2.0)' and pricing tail are slightly promotional but still useful.

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, no-annotation, no-output-schema tool, the operational context (limits, cost, privacy) is good, but the description leaves key calling details uncovered: response shape is only hinted at through 'OpenAI-compatible', and temperature and the 40-message cap are undocumented anywhere.

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 explain all three parameters. It only indirectly explains max_tokens via the '1024 output tokens' ceiling (already encoded as a schema maximum), and says nothing about temperature, the role enum, or the maxItems=40 limit on messages.

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 (chat completions) plus the exact model, license and hosting location, so an agent knows precisely what capability is on offer. It does not need to differentiate from the Portuguese-language sibling tools, which are unrelated, but it also never says how it differs from any other chat/completion endpoint.

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 nature of the tool: 'chat completions' suggests conversational or text-generation tasks. There is no explicit when-to-use, when-not-to-use, or alternative named, so an agent must infer the selection criteria.

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 does well: it discloses the calibration metrics (AUROC 0.94, 1.7% false accusations), clarifies that the output is a probability level and never proof, states text is not stored, and notes the $0.03 x402 price. It does not cover rate limits, latency, or authentication mechanics beyond the price mention.

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 efficient sentence front-loads the core purpose, then packs accuracy, output interpretation, privacy, and cost into compact clauses. Every phrase 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 one-parameter tool with no output schema, the description covers purpose, accuracy, output semantics, privacy, and cost—enough for correct invocation. It stops short of specifying the exact return format (e.g., numeric range or category labels), which would fully close the loop.

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 single 'texto' parameter (max 8000 chars, ideally 90+ words) is already documented. The description adds useful language specificity by emphasizing PT-PT rather than generic Portuguese, but does not otherwise elaborate on parameter constraints or input expectations.

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 resource and task: an AI-generated text detector specialized for European Portuguese (PT-PT), including the underlying Binoculars method. It is clearly distinct from the sibling tools (localization, ad verification, etc.), though it does not explicitly name or contrast 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?

Usage is implied by the purpose—submit Portuguese text to get an AI-detection probability—and the caveat 'never proof' guides interpretation. However, there is no explicit when-to-use guidance, no stated alternatives, and no exclusions or prerequisites beyond the per-call price.

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 burden and does well: it discloses the pipeline (rule-based detection, local LLM rewrite, re-check), the no-op path that avoids the LLM, that text is not stored, and the $0.01/x402 cost. It stops short of stating the exact return shape (rewritten string vs. structured report), which is the main remaining 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?

One dense paragraph, front-loaded with the transformation and its mechanics, followed by no-op behavior, privacy, and price. Every clause adds distinct information; nothing is repeated from the schema.

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 one-parameter tool with no annotations and no output schema, the description covers cost, data retention, and fallback behavior. Only the precise response format is left implicit, which is a minor omission given it hints that unchanged text is returned.

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% and the single parameter already documents the expected input language and 4000-char cap, so the description adds no syntax or format detail beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 (rewrites) and resource (Brazilian Portuguese → European Portuguese) plus the concrete transformations applied (vocabulary, gerund → 'a + infinitive', 'você'). An agent immediately understands the transformation 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?

Implies usage (you have BR Portuguese text you want in PT-PT) and notes the no-op case when text is already PT-PT, but gives no explicit when-to-use/when-not framing and does not mention any alternative among chat-gpt-oss, detetor-ia-pt, margem, or verificar-anuncio.

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 burden and does disclose two real behavioral facts: exact decimal arithmetic (no float rounding surprises) and commission applied on gross price, plus a $0.005-per-call x402 payment requirement. It says nothing about permission/auth flow, sign conventions for negative margins, rounding of results, or default values for the 5 optional inputs.

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 front-loaded sentences: what is computed, then cost factors, then precision guarantee, then price. Zero filler and the pricing disclosure is compact.

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 stateless calculator with no output schema, an agent still needs to know the result shape (single margin figure vs. breakdown) and the percentage/currency conventions. Those gaps matter for a financial tool, though the list of included factors means the agent can call it without guessing wrong inputs in most cases.

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% and parameter names are Portuguese, so the description must compensate. It effectively maps the concepts iva_pct (VAT), portes (shipping), comissao_pct (commission), taxa_fixa (fixed fee) and devolucoes_pct (returns). However, it gives no unit convention (is iva_pct 23 or 0.23?), no defaults for the 5 optional fields, and does not directly label preco_venda/custo_produto — the two required parameters.

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 computation (per-sale profit margin) and enumerates the exact cost components it accounts for: VAT, shipping, marketplace commission on gross price, fixed fee and returns. It is domain-scoped to Portugal e-commerce. No sibling differentiation is offered, but the siblings (chat-gpt-oss, detetor-ia-pt, localizar-pt-pt, verificar-anuncio) are unrelated utilities, so confusion is unlikely.

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?

'Per-sale' implicitly scopes it to single-transaction calculation rather than aggregate reporting, which is useful. But there is no explicit statement of when to use it, prerequisites, or what alternative to pick for other computations. Usage is inferable 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?

With no annotations, the description carries the full behavioral burden. It usefully discloses that the tool is deterministic and costs $0.01 per call via x402, which are important operational facts. However, it omits auth requirements, return format, error behavior, and rate limits.

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 tight sentences that front-load the core purpose, followed by a compact list of checks and key behavioral facts. Every phrase earns its place, with no redundancy or 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 tool with five parameters, no output schema, and no annotations, the description is only partially complete. It clarifies what is checked and notes pricing and determinism, but leaves the agent without usage guidelines, most parameter meanings, or any sense of the output structure.

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 description provides no parameter-level semantics beyond what the schema already covers. With 60% schema description coverage, two parameters ('produto' and 'afiliado') lack any description in both the schema and the description, so the agent gets no guidance on their meaning or expected values.

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 ('Checks') and resource ('Portuguese ad/video copy') and enumerates the exact compliance rules checked. It does not explicitly differentiate from sibling tools, but the purpose is far more specific than the siblings' domains (chat, AI detection, localization, margin).

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-to-use guidance is given. It does not mention alternatives or prerequisites (e.g., when to choose this over detetor-ia-pt or other siblings). The agent is left to infer usage from the purpose alone.

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