Uau · Essa é Minha

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

Annotations only say readOnlyHint=true and openWorldHint=true; the description adds that pricing follows an official table, that back-printing carries a per-piece surcharge, that freight comes from Correios with both PAC and SEDEX options, and that freight/production time only appear when CEP is supplied. It does not cover error handling for malformed CEP or whether shipping is silently omitted, so it stops short of 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?

A single front-loaded sentence that leads with price and appends the CEP-conditional freight clause. It is dense with comma splices but contains no filler; a slightly clearer structure would earn a 5.

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 5-parameter tool with a nested quantity object and no output schema, the description succeeds in naming the return concepts (price, PAC/SEDEX freight, production deadline) and their conditions. Only minor unknowns remain — currency, error behavior, and what exactly is returned when CEP is absent — so it is nearly complete but not fully.

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 already 80%, yet the description still adds real meaning: quantities are aggregated as a total for pricing, frente_e_verso triggers a per-piece surcharge, cep unlocks freight computation, and cor informs the production deadline. The only gap is that modelo (an enum with no schema description) remains unexplained by either source.

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?

Names the exact outputs: price from the official table for the total quantity, optional back-printing, and — when CEP is given — Correios PAC/SEDEX shipping plus production deadline. The verb 'calcular' plus these resources clearly separates it from siblings like fechar_compra or montar_link_de_compra, though it never names an alternative explicitly.

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: an agent can infer this is the quoting tool to call before fechar_compra, and that supplying CEP adds freight. There is no explicit when-to-use/when-not statement nor any pointer to the availability or catalog tools that would supply modelo/cor inputs.

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=false, so safety is covered. The description adds that the link comes with the message already embedded, but says nothing about the returned format (URL string?), whether it opens a chat directly, or any side effects. Modest added value over 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?

Two short sentences, front-loaded with the core resource and followed by usage contexts. No filler, though the grammar is slightly elliptical and the actual action verb is omitted.

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?

With one optional parameter, no output schema, and read-only annotations, the description is close to sufficient but leaves open what the tool returns and whether 'mensagem' is required. Adequate minimum, not complete.

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 some compensation is expected. 'Já com a mensagem' hints that the single parameter is the pre-filled message text, but it never names the 'mensagem' parameter, its 800-character limit, or that it is optional.

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 the resource (a WhatsApp link to Camila, with the message pre-filled), which is specific and distinguishable from sibling tools like montar_link_de_compra. The verb is implicit (the tool produces/returns a link) rather than explicitly stated, so it falls just short of 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?

Gives concrete usage contexts ('para grupos, eventos, prazos especiais ou dúvidas') that tell the agent when this tool is appropriate. It does not name alternatives or exclusions (e.g., when to use a purchase link or catalog tool instead), so it stops short of 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 declare a write operation (readOnlyHint=false, idempotentHint=false), and the description adds the crucial behavioral fact that the first call is a pure quote with no side effects, which is not inferable from the annotations. It does not cover permissions, error behavior, or whether retries duplicate orders, so it stops short of 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?

Three short sentences: what it does and returns, the two-step gate, and the routing to the alternative. Front-loaded and every sentence carries load.

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 an 11-parameter, nested, non-idempotent write tool with no output schema, the description covers the creation flow, the safe quoting path, and the return payload. It leaves gaps on failure/duplicate-submission behavior, but the agent has enough to invoke it correctly in the normal path.

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 27%, so many nested parameters (comprador, endereco, frete, verso, quantidade_por_tamanho) rely on the schema alone. The description does add real meaning for the pivotal confirmo_total parameter beyond its schema note (it must equal the quoted total and requires buyer approval), which keeps it at 3 rather than lower.

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 ('Cria o pedido') plus what it returns (Pix copia e cola and Mercado Pago card link). It also explicitly separates itself from the sibling montar_link_de_compra by noting that this tool uses text art, not image art.

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?

Gives an explicit two-stage protocol: without confirmo_total it only calculates the total and creates nothing; with confirmo_total matching the total and the buyer's approval, it creates the order. It also names the alternative (montar_link_de_compra) and the condition that selects it.

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=false, so the safety profile is covered. The description adds that the link opens a simulator where the user adjusts the print and pays on the site, giving useful downstream context, but it omits URL lifetime, what exactly is returned, and any limits or side effects.

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 short sentences with little wasted text. The second sentence is user-journey context rather than invocation detail, so the description is not maximally front-loaded for an agent, but it is still concise.

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 no output schema, a nested input object and low schema coverage, the definition is thin. It never states that the tool returns a URL, whether the link expires or is single-use, or how the size-quantity object should be shaped, leaving too much for the agent to infer.

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 25%, so the description needs to compensate. It loosely names modelo, cor, tamanhos and frase, but does not explain the nested quantidade_por_tamanho map, that only modelo is required, the allowed enum values, or the frase max length, so it adds little beyond property names.

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 that the tool produces a simulator link pre-filled with model, color, sizes and phrase, so the resource is identifiable. However, it is a noun phrase rather than a clear verb-led action, and it does not distinguish the tool from siblings like fechar_compra or calcular_preco.

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?

Provides no explicit when-to-use or when-not-to-use guidance. It describes a downstream user flow (adjust print, preview, pay on site) but does not say whether this should be called before fechar_compra, instead of calcular_preco, or under what conditions.

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=false, so safety and data locality are covered. The description usefully adds that the payload is an information bundle (price tiers, surcharge, deadlines, freight), but says nothing about return shape, size, or whether the listed prices are authoritative versus requiring calcular_preco.

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 short sentence with no filler, and each listed item defines real scope. It is a bare noun list without a leading verb or grouping (info vs pricing vs logistics), so it is dense rather than optimally front-loaded.

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?

With zero parameters, a read-only annotation and no output schema, the description is nearly sufficient to know what comes back. However, in a six-tool purchase flow it never clarifies its relationship to calcular_preco or ver_disponibilidade, leaving an agent unsure whether the catalog's price table and lead times are definitive or merely indicative.

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 takes zero parameters, so the baseline is 4; there is nothing parameter-related for the description to compensate for. No misleading parameter hints are present.

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 enumerates exactly what the catalog returns (models, colors, sizes, price table by quantity, back-side surcharge, lead times, shipping, how to buy), which tells an agent this is a static product/info lookup. The verb is carried only by the name/title ('Ver catálogo'), and nothing in the text distinguishes it from siblings like calcular_preco or ver_disponibilidade, which also touch pricing and lead times.

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 statement of when to call this versus calcular_preco, ver_disponibilidade, or montar_link_de_compra — all plausible adjacent steps in a purchase flow. The 'como comprar' item faintly implies a starting-point role, but the agent must infer that; no conditions or exclusions are given.

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=false, so the safety profile is covered. The description adds genuinely useful behavioral context — the lead times of 3 days vs 15 business days and the rule that nothing is ever out of stock because items fall back to made-to-order — but says nothing about the shape or granularity of the returned availability data.

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 compact sentences that front-load the core concept and then explain the two states. There is mild redundancy in 'pronta entrega, fica pronta em até 3 dias', but nothing extraneous overall.

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 lookup with no output schema, the description covers the semantics of the result values but not the structure of the response (which sizes are listed, how per-model/per-colour results are grouped). Given the tool's simplicity and the readOnly annotation, it is adequate but leaves a real gap an agent would want filled.

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%: cor carries its own description and default behaviour ('Sem cor, devolve todas'), while modelo has none. The description adds no meaning about either parameter and its 'por tamanho' framing does not map onto modelo/cor, so it neither compensates for the gap nor clarifies the enum choices.

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 resource — live availability — and defines the two availability states it returns, which makes it distinguishable from ver_catalogo in principle. However, it says availability is 'por tamanho' while the schema exposes modelo and cor, so an agent cannot immediately tell whether 'tamanho' is a return dimension or a missing parameter — a small ambiguity in an otherwise clear 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?

The description explains what the availability values mean but never says when to call this tool versus siblings such as ver_catalogo, ver_pedido, or fechar_compra, nor does it state any prerequisite (e.g., check availability before closing an order). Usage must be inferred.

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=false, so the safety profile is covered. The description adds real value by disclosing the possible outcomes (waiting for payment vs. paid) and that the order number is part of the response; it does not cover behavior for an unknown/invalid id, 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?

A single compact sentence that front-loads the return semantics and only then the origin of the input. Nothing redundant.

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?

With one required parameter, no output schema and annotations covering the read-only nature, the description is nearly sufficient: it explains what comes back (status and order number). Only edge-case behavior (invalid or unknown order id) is left unspecified.

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 the single parameter already documents that it is the 'compra' id returned by fechar_compra. The description echoes that provenance but adds no format or usage detail beyond the schema, so baseline 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?

Names a specific resource (a purchase/order) and states exactly what is returned: its situation, either awaiting payment or paid, plus the order number. It also anchors the tool to the sibling that creates the input (fechar_compra), which distinguishes it from ver_catalogo/ver_disponibilidade.

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 'compra feita por fechar_compra' makes the usage context explicit: call this after closing a purchase to check its status. No alternative tool is named or excluded, but the sequencing guidance is unambiguous.

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