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 only states the action 'Baixa' without adding context about permissions, side effects, or error scenarios. It does not reveal whether the operation is read-only, what happens if the NF-e does not exist, or any prerequisites.

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, concise sentence with no wasted words. It front-loads the action and resource, making it easily scannable.

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 one-parameter tool with no output schema, the description is minimal but adequate. However, it lacks details such as the expected return (binary PDF), prerequisites, or error handling, which would be valuable for an agent to invoke it 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 schema description coverage is 100% for the single parameter 'id', providing its meaning ('ID da NF-e na Nuvem Fiscal'). The tool description itself adds no additional parameter semantics, but the baseline of 3 applies due to high schema coverage.

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 uses a specific verb 'Baixa' (downloads) and a specific resource 'PDF do DANFE de uma NF-e', clearly distinguishing it from sibling 'baixar_xml_nfe' which downloads XML. It unambiguously states what the tool does.

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 implies usage (download the PDF of an NF-e) but does not explicitly mention when to use this over alternatives like 'baixar_xml_nfe'. No exclusions or alternative guidance is provided, relying on the tool name for differentiation.

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 of behavioral disclosure. It states the core download action but does not clarify what the response contains (e.g., binary file, base64 string, URL) or any authentication/side effects. This leaves ambiguity for an agent.

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, direct sentence that is front-loaded with the verb and resource. No wasted words or redundant information.

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 download tool with one parameter and no output schema, the description is minimally adequate but lacks details about return format and differences from the similar baixar_pdf_nfe tool. The absence of annotations increases the need for more context.

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 schema already provides 100% coverage for the single 'id' parameter with a clear description. The tool description adds no additional semantic information, so it meets the baseline for high schema coverage.

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 uses the specific verb 'Baixa' (downloads) and identifies the resource as the signed XML of an NF-e, clearly distinguishing it from sibling tools like baixar_pdf_nfe which download the PDF version.

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 is provided on when to use this tool versus alternatives such as baixar_pdf_nfe or consultar_nfe. The description is purely factual and does not mention prerequisites or exclusions.

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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states the registration action without detailing side effects, persistence, authorization, duplicate handling, or changes to company data. For a mutation tool, this is a significant transparency 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?

The description is a single concise sentence that is front-loaded with the verb and resource. It contains no redundant information or unnecessary details, making it easy to parse and act upon.

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?

Given the tool's low complexity (one parameter, no output schema), the description provides sufficient context by linking registration to invoice issuance. It lacks explicit side-effect or response information, but for a simple create operation with a well-documented parameter schema, it is adequately 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?

The schema description covers 100% of the parameter, describing 'dados' as a JSON string with company data (CNPJ, razão social, endereço, regime tributário, etc.). The tool description adds no additional parameter meaning beyond this, so the baseline score of 3 for full schema coverage 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 clearly states the action ('Cadastra' = registers), the resource ('nova empresa na Nuvem Fiscal'), and the purpose ('para emissão de notas fiscais'). This distinguishes it well from sibling tools like emitir_nfe, cancelar_nfe, and consultar_empresa by focusing on the creation/registration 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?

The description implicitly provides usage context: it is the registration step needed before issuing fiscal notes. It does not explicitly mention when not to use it or name alternatives, but the purpose is clear enough for an agent to select it appropriately among the invoice-operation siblings.

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. It discloses the 24-hour regulatory window, but it does not mention potential side effects (e.g., contacting SEFAZ, irreversibility, or error behavior if the deadline is missed). For a destructive/mutation operation, this is a significant 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?

The description is a single, front-loaded sentence that immediately states the action and the critical constraint. There is no redundant wording or filler, so every word 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?

This is a write/state-changing operation with no annotations, no output schema, and only a terse description. It lacks information about expected outcomes, failure modes, or preconditions beyond the 24-hour rule. The simple schema (2 params) reduces complexity, but the description still leaves important operational context unexplored.

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 100% coverage with clear descriptions for both parameters ('ID da NF-e na Nuvem Fiscal' and 'Motivo do cancelamento (mínimo 15 caracteres)'). The description adds no additional parameter-specific meaning beyond what the schema states, so the baseline score of 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?

The description clearly states the action ('Cancela uma NF-e autorizada') and specifies the target resource (NF-e) plus the status (authorized). It also adds a key condition (within 24 hours), which helps distinguish it from sibling tools like inutilizar_nfe and cancelar_nfse.

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 provides a clear temporal condition ('dentro de 24h após a autorização') that tells the agent when cancellation is valid. However, it does not explicitly mention alternatives or exclusions, such as 'use inutilizar_nfe if the NF-e is not authorized' or 'for NFSe, use cancelar_nfse'.

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 for disclosing behavioral traits. It only states the action 'Cancela' without revealing consequences, reversibility, authorization requirements, or side effects. For a cancellation tool, this is a significant omission.

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, direct sentence with no redundant words, making it highly concise and easy to parse. It is appropriately front-loaded with the verb and resource.

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 tool is simple with two fully described parameters, but it lacks output schema and annotation support. The description gives only the basic action and omits any context about the cancellation process, status constraints, or expected results, leaving some information gap for the agent.

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 full descriptions for both parameters (id and justificativa) with 100% coverage. The description adds no parameter-level information, so a 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 clearly states the tool's function with a specific verb ('Cancela') and resource ('NFS-e'), distinguishing it from sibling tools like cancelar_nfe which targets a different document type. The word 'emitida' adds context that it operates on issued invoices.

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 no explicit guidance on when to use this tool versus alternatives, such as cancelar_nfe. The resource type NFS-e implicitly signals its domain, but there is no mention of exclusions, prerequisites, or when other tools might be more appropriate.

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. It discloses a key behavioral constraint (cannot correct tax-affecting fields) and the authorized NF-e prerequisite. However, it does not mention side effects, transmission to SEFAZ, or what happens on success/failure, leaving moderate gaps.

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 primary purpose and immediately follows with key constraints. It is concise with no wasted words.

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 only 2 parameters, both fully described in the schema, and no nested objects, the description adequately covers the main scope and a significant restriction. It could mention response format or transmission details, but given the simple interface, it is reasonably 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 100% with both 'id' and 'correcao' having meaningful descriptions. The tool description adds no additional parameter context beyond what the schema already provides, 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 clearly states the action ('Emite' = issues) and the specific resource ('Carta de Correção (CC-e) para uma NF-e autorizada'). It distinguishes itself from siblings like cancelar_nfe and emitir_nfe by focusing on the correction letter use case.

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 includes explicit restrictions ('Não pode corrigir valores, CFOP, ou dados que alterem o cálculo do imposto'), which serve as when-not-to-use guidance. It also specifies the prerequisite that the NF-e must be 'autorizada'. However, it does not name alternative tools for other correction scenarios.

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?

No annotations are provided, and the description relies on 'Consulta' to imply a read-only operation. It adds the scope of public data and sample fields, but does not explicitly address side effects, permissions, or error behavior, which is a moderate gap given no 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?

The description is a single sentence that front-loads the action and conveys essential information without waste.

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 read tool with one parameter and no output schema, the description gives a useful overview including the source and sample fields, but it stops short of describing response structure or potential failure modes. Given low complexity, this is largely sufficient.

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 schema covers the only parameter 'cnpj' with a clear format description. The tool description adds no additional parameter context beyond what the schema provides, so it meets the baseline for high schema coverage.

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 verb 'Consulta' (queries) and the resource 'dados públicos de um CNPJ na Receita Federal', listing example fields. It differentiates from sibling tools by focusing specifically on CNPJ public data from the federal revenue service.

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 implies the tool is for checking public CNPJ data but does not discuss when to use it versus alternatives like 'consultar_empresa', nor mention any exclusions or contextual triggers.

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?

No annotations are provided, so the description carries the full burden. 'Consulta' implies a read operation, but the description does not disclose return data format, behavior when the company is not found, data freshness, or any side effects. It adds minimal behavioral context beyond the verb.

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, concise sentence that immediately states the tool's action and scope. No filler or redundant information is present.

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 a simple one-parameter lookup, but with no output schema or annotations, the vague term 'dados' leaves out what data is returned and how errors are handled. It is adequate for a minimal lookup but lacks useful operational context.

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 has 100% description coverage for the single parameter ('CPF ou CNPJ da empresa'). The tool description adds no additional format, validation, or usage detail, so the baseline score 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 uses a specific verb ('Consulta') and identifies the resource ('dados de uma empresa cadastrada na Nuvem Fiscal'), clearly distinguishing this internal company lookup from the sibling tool 'consultar_cnpj' which likely queries external CNPJ data.

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 is provided about when to use this tool versus alternatives like 'consultar_cnpj' or 'cadastrar_empresa'. There are no explicit exclusions, prerequisites, or contextual instructions.

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 burden of disclosing behavior. The word 'Consulta' (queries) indicates a read operation, but it does not explicitly state that it is read-only, mention authentication needs, or describe the response format. This is minimal but adequate for a simple query tool.

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, compact sentence that conveys all essential information without any filler or redundant words. It is perfectly 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?

For a simple one-parameter fetch operation, the description is nearly complete: it states what it does and which ID to use. However, since there is no output schema, it could have been more explicit about what 'detalhes' are returned (e.g., status, values, tax info), though sibling tools like baixar_pdf_nfe and baixar_xml_nfe hint that this returns JSON data.

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% with the single 'id' parameter clearly described as 'ID da NF-e na Nuvem Fiscal'. The description repeats 'pelo ID' but adds no extra semantics beyond what the schema already provides, 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 uses the specific verb 'Consulta' and identifies the resource as 'os detalhes de uma NF-e específica pelo ID', clearly indicating a single-record query. This distinguishes it from siblings like listar_nfe (listing all NF-es) and consultar_nfse (service invoices).

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 implies usage when you have a specific NF-e ID and need details, but it does not explicitly mention alternatives or state when not to use it. There is no direct comparison with listar_nfe or consultar_nfse, leaving the guidance implicit.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The word 'Consulta' implies a read-only operation, but the description does not explicitly state that it is non-destructive, nor does it mention possible errors, response format, or other behavioral traits. It adds minimal context beyond the tool's name.

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, clear sentence with no redundant words. It efficiently conveys the core purpose and key parameter without any fluff, earning a perfect score for conciseness and structure.

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?

Given the low complexity (one parameter, no output schema), the description is minimally viable. It tells the agent what the tool does and how to identify the target NFS-e, but it does not explain what 'details' will be returned or any error behavior. The lack of an output schema means the description could have elaborated on return values, but the simplicity of the lookup partially compensates.

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 has 100% description coverage for the single parameter 'id', which is already described as 'ID da NFS-e na Nuvem Fiscal'. The description repeats this by saying 'pelo ID' but does not add additional meaning or usage details. With full schema coverage, 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 clearly states the tool's action ('Consulta') and its resource ('detalhes de uma NFS-e específica'), and explicitly identifies the lookup key ('pelo ID'). This distinguishes it from sibling tools like 'listar_nfse' (which lists multiple) and 'emitir_nfse' (which creates NFS-e).

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 implies the tool should be used when you need details of a specific NFS-e identified by its ID, and there is a sibling tool 'listar_nfse' likely for broader queries. However, it does not explicitly state when to use this over alternatives, nor does it provide any exclusions or prerequisites. The usage context is clear but not explicit.

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 full burden for behavioral disclosure. It only states the requirement for complete JSON data, but does not mention authentication needs, potential side effects, idempotency, success/failure indicators, or response behavior. The mutation nature is implied by 'emite' but not elaborated.

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, succinct sentence that leads with the action and then states the key requirement. No filler or redundancy, making it easy to parse quickly.

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 tool is simple with one parameter, but the absence of an output schema and annotations means the description should clarify return values or permissions. It does not, and while the core purpose is clear, the description is not fully complete for a production usage context.

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% as the only parameter 'dados' has a detailed description covering the JSON structure and typical fields. The tool description adds minimal extra meaning (emphasis on 'completeness') beyond the schema, so the baseline score of 3 for high schema coverage 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 opens with 'Emite uma nova Nota Fiscal Eletrônica (NF-e)', which is a specific verb (emite) plus resource (NF-e), clearly distinguishing it from sibling tools like cancelar_nfe or baixar_pdf_nfe. The addition of 'nova' and the requirement for complete JSON data further disambiguates this as the creation tool.

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 implies usage when you need to issue a new NF-e and have complete data, but it does not explicitly mention alternatives or when not to use the tool. Sibling tool names provide contextual contrast, but the description itself lacks explicit guidance or exclusions.

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?

No annotations are provided, so the description carries the full burden. It discloses that the tool issues a new NFS-e (a write operation) and requires complete JSON data, but it does not mention side effects, authentication, reversibility, or response 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?

Two short sentences, front-loaded with the core purpose and a concise requirement. Every word adds value.

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?

Given the simple schema (one param, no output schema) and the absence of annotations, the description covers the basics. However, for a tool that issues a legal tax document, it omits important context about consequences, authorization, and validation.

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%: the single parameter 'dados' is described as a JSON string per the Nuvem Fiscal API. The description adds emphasis on 'complete' data, but this is a minor addition over the schema's own documentation.

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 it emits a new NFS-e, using the specific verb 'Emite' and naming the exact resource. This distinguishes it from sibling tools like 'emitir_nfe', which issues a different type of fiscal document.

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 implies usage for emitting NFS-e but does not explicitly contrast with alternatives such as emitir_nfe or provide exclusion criteria. It gives a requirement ('dados completos em formato JSON') but lacks when-to-use 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 provided, the description carries the full burden of disclosing side effects. It says the tool 'inutiliza' a range, but does not mention that this is typically an irreversible, government-registered operation, nor does it explain prerequisites, permissions, or consequences. This is a significant gap for a write operation.

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, focused sentence with an active verb and an illustrative example. It avoids fluff and front-loads the obvious action, making it easy to parse quickly.

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 description captures the core purpose and an example scenario, and the schema thoroughly details parameters. However, with no output schema and no annotations, it omits information about expected results, error conditions, or integration behavior with SEFAZ, leaving notable gaps for a tool with 7 parameters.

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 schema provides descriptions for all seven parameters (100% coverage), so the baseline is 3. The description's phrase 'faixa de numeração' loosely maps to numero_inicial and numero_final, but adds no additional semantic detail beyond what the schema already provides.

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 action ('Inutiliza') and the resource ('faixa de numeração de NF-e'), with an explicit example ('falhas de sequência'). This distinguishes it from sibling tools like cancelar_nfe, which cancel individual issued invoices, whereas this invalidates an unused range of numbers.

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 a clear context for use: numbers that will not be used (e.g., sequence failures). It implies when to use the tool, but does not explicitly contrast with alternatives or state when not to use it, so it falls short of full exclusion 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. It neither confirms this is a read-only operation nor discloses any behavioral details such as result limits (top/skip) or environment selection (ambiente). The action is simple, but no additional context is given beyond the basic listing.

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 with no filler. Every word contributes to the purpose.

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 4 parameters, no output schema, and no annotations, the description is too terse. It omits pagination behavior, environment significance, and what the response contains, making it incomplete for an agent to use 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?

Schema already covers 100% of parameters with descriptions. The tool description adds no extra meaning beyond the schema; it aligns with the cpf_cnpj parameter but provides no additional nuance for top, skip, or ambiente.

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 uses the specific verb 'Lista' (list) and identifies the resource 'NF-e' with a clear scope 'emitidas por um CNPJ/CPF', distinguishing it from issue/cancel/download operations. It is unambiguous and tells exactly what the tool does.

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 is provided on when to use this tool instead of alternatives like 'consultar_nfe' or 'listar_nfse'. The description only states what it does, with no exclusions or context about pagination or environment selection.

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?

No annotations are provided, so the description bears the responsibility for behavioral disclosure. The verb 'Lista' implies a read-only operation, but the description does not disclose whether canceled invoices are included, result ordering, pagination behavior (beyond schema), or response format. It adds limited context beyond the action itself.

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, focused sentence with no extraneous words. It conveys the essential purpose efficiently and 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?

This is a simple list tool with a small schema, but no output schema or annotations exist. The description defines the core functionality and filter, but omits details about the returned payload, status filtering, or how to handle pagination in practice. It is adequate for a basic list tool but leaves room for more context.

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%: all three parameters (cpf_cnpj, top, skip) have clear descriptions. The tool description adds no additional parameter information beyond what the schema already provides, so the baseline of 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?

The description clearly states the tool's function: 'Lista as NFS-e emitidas por um CNPJ/CPF' (Lists the NFS-e issued by a CNPJ/CPF). It uses a specific verb 'Lista' and identifies the resource (NFS-e) and scope (by CNPJ/CPF), distinguishing it from siblings like 'listar_nfe' (which lists NFe) and 'consultar_nfse' (which likely retrieves a single invoice).

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 implies usage: use this when you need to list NFS-e for a given CNPJ/CPF. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or comparisons to sibling tools such as 'consultar_nfse' or 'listar_nfe'.

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?

No annotations are provided, so the description must carry the full burden. It only states 'verifica' without disclosing any behavioral details such as return format, safety (read-only), or error behavior. For a status-check tool, the absence of any details about what the agent can expect leaves a significant 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?

The description is a single, clear sentence that front-loads the core action. It contains no filler and is appropriately concise 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?

The tool is simple with two parameters and no output schema. The description adequately conveys the purpose but omits mention of the return value or what 'online' means in practice. While the name and description together imply a status result, the lack of any output specification leaves some ambiguity for an agent.

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 high coverage (100%) with descriptions for both parameters ('Sigla da UF' and 'Ambiente'). The description adds no additional parameter-specific meaning, so it does not exceed the schema's baseline contribution.

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 purpose with a specific verb ('Verifica') and resource ('serviço da Sefaz para uma UF'), making it distinct from sibling tools that handle NFe/NFSe operations. It unambiguously identifies the check of Sefaz service availability for a state.

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 purpose implies when to use the tool: to verify service availability for a specific UF. No alternatives are mentioned, but there are no sibling tools with similar functionality, so the context is clear. It lacks explicit 'when not to use' guidance, but this is not critical given its uniqueness.

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