Consultas

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

The description goes beyond annotations by explaining that a token in config gives a permanent, non-expiring connection, whereas pasting a token provides only session-scoped login. It also discloses that calling with no arguments yields a link. Given the annotations already convey safety and idempotency, this is meaningful added behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is reasonably concise and front-loaded with the tool's use context, then clearly enumerates the two options. Minor run-on structure and a slightly awkward first phrase keep it from being maximally polished.

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 single-parameter authentication tool with no output schema, the description provides enough context to invoke it correctly: the browser flow, token behavior, how to pass the token, and the no-args link path. It lacks explicit statements about what happens on success or error, but these are not essential for this tool's basic use.

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 only a bare 'token' string property, but the description explains that token is a JWT to be pasted after login, that it is optional, that calling without it generates a login link, and that passing it enables session-only login. This fully compensates for the zero 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 identifies the tool as authentication/login (`log in in the browser`, `session-only login`) and distinguishes it from sibling tools by its specific browser/token flow. It also states the two concrete invocation modes: providing a JWT or requesting a link.

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 when to use each form: permanent setup via config header, session-only via token argument, and link generation with no args. It does not explicitly contrast authentication with alternative tools like connect, so it stops slightly short of full when/not 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is known. The description adds value by specifying the output behavior in two distinct states (all connected vs. missing credentials), mentioning fields like authenticated, pending, and connect_url. This goes beyond the bare annotations, though it doesn't detail full response structure.

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 sentences, front-loaded with the primary output, and then providing conditional details. Every sentence contributes to understanding the tool's behavior. No redundant fluff.

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 no output schema, the description needs to explain return values, and it does by mentioning 'authenticated:true', 'pending[]', and 'connect_url'. It also covers two main scenarios. While not exhaustive, it is sufficient for a simple read-only status tool, especially given the annotations indicate non-destructive, idempotent behavior.

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

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

The tool has zero parameters, so there is nothing to document. The schema coverage is 100% (vacuously), and the baseline score for zero parameters is 4. Description adds no parameter info, which 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 purpose: 'Returns connection status and URLs.' It distinctly separates from siblings like 'authenticate' (which performs authentication) and the various 'consultas_*' tools (which query external data). The description also specifies the two possible outcomes based on connection state, adding specificity.

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 clear context on when to use this tool—when checking connection status and obtaining URLs. It does not explicitly exclude other tools or name alternatives, but the role is clear enough for an agent to differentiate from 'authenticate' or data-query tools. No explicit when/alternative guidance, but the action is unambiguous.

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 the tool as read-only (readOnlyHint=true) and non-destructive (destructiveHint=false), so the description doesn't need to repeat these. It adds the specific scope (SP state) and query method (by name), which is useful context beyond the annotations. However, it does not disclose potential side effects like rate limits or authentication requirements, though these are not critical for a simple certificate query. The description is consistent with 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?

The description is extremely concise—a single sentence that immediately states the tool's purpose and scope. It avoids unnecessary verbiage and is easy to scan, which is ideal for an agent parsing tool definitions. No redundancy with the tool name or annotations.

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 is clear but somewhat incomplete for a tool that requires three mandatory fields. It doesn't specify the return format (e.g., PDF, text) or any additional requirements like age verification or data privacy considerations. However, the tool is conceptually simple (a lookup), and the lack of an output schema or nested objects reduces the need for extensive explanation. The missing clarity on required parameters and potential use cases makes it only moderately 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 input schema lists three required parameters (nome, genero, birthdate) with zero descriptions, and the tool description only mentions 'by name' ('por nome'), partially covering the 'nome' parameter. It fails to explain the need for 'genero' and 'birthdate', which are likely necessary for disambiguating individuals in criminal records. With schema coverage at 0%, the description carries the burden of explaining parameters, and it inadequately compensates, leaving agents uncertain about the purpose of these fields.

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: obtaining a criminal background certificate for the state of SP, with a focus on name-based queries. It specifies the resource (criminal records) and scope (SP state), which distinguishes it from sibling tools like 'consultas_sintegra_sp' or 'consultas_cnd_federal'. However, it doesn't explicitly differentiate from all siblings (e.g., other state-specific consultations), so it's clear but not fully distinguished.

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 that this tool is for querying criminal antecedents in São Paulo state, using the person's name. It gives a general sense of when to use it, but does not mention alternatives or when to avoid it. Sibling tools like 'consultas_antecedentes_federais' are not referenced, so an agent lacks explicit guidance on choosing between them. The context 'por nome' hints at the primary input, but there's no exclusion of other use cases.

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 establish read-only, idempotent, non-destructive behavior. The description adds useful behavioral context by stating 'Síncrono' and clarifying that the tool checks for reclaimable forgotten money, going beyond what the annotations alone provide.

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 compact: one purposeful opening sentence and one sentence for input guidance. Every sentence earns its place, and the most important information is 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?

Given the low complexity, good annotations, and absence of an output schema, the description sufficiently covers what the tool does, the supported entity types, and the required input pairing. It could add result-shape details, but it is not incomplete enough to hinder selection or invocation.

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%, so the description must compensate. It adds meaningful semantics by pairing cpf with data_nascimento and cnpj with data_abertura_empresa, making the parameter relationships explicit. It stops short of specifying formats such as date style or CPF/CNPJ digit masks.

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 ('verifica') and identifies the exact resource ('Valores a Receber no Banco Central (SVR)'), making the purpose unmistakable. It also distinguishes this tool from sibling consultas tools by focusing on forgotten funds at the Central Bank.

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 clear when-to-use guidance for individual vs. company cases: 'PF: informe cpf + data_nascimento. PJ: informe cnpj + data_abertura_empresa.' This directly tells the agent which parameter combinations apply to which scenario, though it does not explicitly discuss exclusions or alternatives.

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 provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so there is no contradiction. The description adds that this is a state-level lookup by identifiers, but it does not disclose response format, data source, per-state variability, or any required authentication. Beyond the safety profile, behavioral detail is thin.

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 names the certificate type, the query keys, and the required input. It is front-loaded with the essential concept and contains no filler or redundant restatement of the tool name.

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-only query tool with annotations covering safety, the description gives enough to select it, but not enough to invoke it with confidence: it does not specify whether at least one of CNPJ/CPF/IE must be supplied alongside UF, nor what the return value looks like. Since there is no output schema, this gap matters for successful use.

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. It does add meaning by telling the agent that UF is the required state indicator and that CNPJ/CPF/IE are the query keys. However, it does not clarify whether CNPJ, CPF, and IE are mutually exclusive, which one applies to a given entity type, or what formats are expected, leaving ambiguity for invocation.

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 identifies the tool as a query for a state-level negative debt certificate (CND estadual) using CNPJ/CPF/IE and requiring the UF. It distinguishes itself from siblings like consultas_cnd_federal by explicitly saying 'estadual' and 'de um estado', and 'Informe a UF' gives immediate scope guidance.

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 when to use it: when a state-level CND is needed and the UF is known. It does not explicitly name alternatives like consultas_cnd_federal or explain when not to use it, but the state/federal distinction is clear from the wording. This is enough for basic selection but lacks explicit 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds an important behavioral requirement: CPF queries need birthdate. No contradictions with annotations are present.

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 concise sentences, front-loaded with the core purpose and followed by a key conditional requirement. There is no redundant or filler content.

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-only query tool with good annotations, the description covers the essential context: target certificate type, accepted identifiers, and the CPF/birthdate condition. It does not describe return format or error cases, but the term 'Certidão' and the absence of an output schema make the primary return value reasonably clear.

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%, so the description must compensate for the bare input schema. It adds meaning by indicating 'por CNPJ ou CPF' and that CPF requires birthdate. However, it does not specify formats for CPF, CNPJ, or birthdate, nor whether exactly one identifier is mandatory.

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 identifies the tool's purpose: returning a federal tax clearance certificate (CND Federal/PGFN) by CNPJ or CPF. The qualifier 'Federal/PGFN' helps distinguish it from sibling tools like consultas_cnd_estadual, though it lacks an explicit verb such as 'consultar' or 'obter'.

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 useful context by stating that CPF queries also require birthdate, which is a prerequisite for use. However, it does not explicitly state when to choose this tool over alternatives like consultas_cnd_estadual or consultas_cndt; the differentiation is only implied through 'Federal/PGFN'.

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?

Since annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the description doesn't need to restate safety. It adds value by specifying the exact document type (CNDT) and the accepted identifiers (CNPJ or CPF), which tells the agent the nature of the operation and what parameters to expect. There's no contradiction with 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, concise sentence that states the core purpose and parameters. It is efficiently front-loaded with the tool's function and required inputs, with no redundant or filler content.

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 that the tool is a read-only lookup with rich annotations (readOnly, idempotent, non-destructive) and no output schema, the description's brevity is somewhat acceptable. However, it doesn't explain additional context like whether CPF and CNPJ are mutually exclusive, or what the response contains (e.g., certificate status). The lack of parameter format and usage details makes it minimally viable but not fully 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 provides only 'cpf' and 'cnpj' as string types with no descriptions, and schema description coverage is 0%, so the description must compensate. The description does not clarify the format (e.g., with or without punctuation), or explain that either parameter is optional or mutually exclusive. This is a significant gap for parameter understanding.

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: obtaining a CNDT (Certidão Negativa de Débitos Trabalhistas) using either CNPJ or CPF. It identifies the specific resource (labor debt clearance certificate) and the required input types, which is clear and distinguishes it from other consultation tools in the sibling list, though it doesn't explicitly name alternatives.

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 tells users when to use this tool: to obtain a CNDT for a company (CNPJ) or individual (CPF). It does not explicitly state when not to use it or mention alternatives, but the context of sibling tools (e.g., consultas_cpf for general CPF checks) implies this is specifically for labor clearance certificates. Overall, guidance is adequate 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context by enumerating the returned data fields and stating the required CPF and birthdate inputs. It does not mention authentication or error behavior, but the annotation coverage lowers the burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. Every phrase adds information about purpose, output fields, or required inputs.

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-only query tool, the description covers purpose, required inputs, and output fields, and annotations cover safety. However, it omits input formats (e.g., CPF punctuation, birthdate format) and any usage guidance, leaving the agent to guess invocation details.

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 for the two string parameters. It only restates that CPF and birthdate are required, adding no format, validation, or example details beyond what the schema property names already imply.

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 identifies the tool as querying the registration status of a CPF at the Receita and lists the returned fields (name, status, birth, inscription, death). It is specific to CPF and thus distinguishable from sibling consultas_* tools, though it lacks an explicit verb and instead uses a noun phrase.

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 CPF registration lookups and states the required inputs ('Requer CPF + data de nascimento'), but it does not explicitly say when to use this tool versus the many sibling consultas_* tools, nor does it mention exclusions or alternatives.

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, idempotentHint=true, and destructiveHint=false, so the description doesn't need to repeat those. However, it adds no additional behavioral context—no return format, limitations, or authorization requirements. The one-liner is essentially the purpose, not behavioral disclosure beyond 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 concise sentence in Portuguese, front-loaded with the essential information. No wasted words, but it is minimal and lacks structure to elaborate on details.

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 a single parameter and no output schema, the description is too sparse. It doesn't explain what the agent should expect as a return (e.g., certificate validity status) or any additional context like auth requirements. For a simple lookup, this may be enough for a human but leaves an AI agent guessing.

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% and the description only adds 'por CNPJ', which merely restates the parameter name. No format (e.g., digits only, with/without punctuation) or constraints are given. Given the low schema coverage, the description should compensate but doesn't.

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 checks employer regularity with FGTS (CRF) by CNPJ. It uses a specific verb (Regularidade) and resource (FGTS) and distinguishes itself from sibling consultas_* tools that query other data (e.g., CPF, NF-e, Simples).

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 (to check FGTS regularity via CNPJ) but provides no explicit when-to-use, when-not-to-use, or alternative tools. Since there are many sibling consultas tools, guidance on selection would help, but it's not forbidden.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context that the tool returns a receipt/status for a specific calendar year, but it does not disclose output format, possible status values, or any authentication/privacy behavior. No contradiction with 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, front-loaded sentence with no filler or repetition. Every word contributes to identifying the tool's purpose and scope.

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 no output schema and no parameter descriptions, the description carries a heavy burden. It does not explain what 'situação' values might be, why 'birthdate' is required, or how this tool relates to authentication or sibling consultation tools. The description is too minimal to be fully actionable 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?

Schema description coverage is 0%, so the description must compensate. It clarifies that 'cpf' and 'year' refer to a CPF and calendar year, but it does not explain the required 'birthdate' parameter at all, nor does it provide format expectations for any parameter. This is a significant gap for a 3-parameter tool.

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 identifies the resource (IRPF declaration for a CPF) and the kind of result (comprovante/situação), and the calendar-year scoping distinguishes it from sibling consultas tools. However, it lacks an explicit verb like 'consult' or 'retrieve', so it stops 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?

Usage is implied by the resource name and domain: it is the tool for IRPF declaration status. There is no explicit guidance about when to use it versus alternatives, no exclusions, and no mention of prerequisites such as authentication, so it only reaches the 'implied usage' level.

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 destructiveHint false, so the safety profile is covered. The description adds the specific scope (by holder) but doesn't disclose output format or any additional behavioral constraints, which is acceptable given the read-only nature.

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?

Single, concise sentence in Portuguese that captures the essence. No redundancy, clearly 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 read-only query tool with two optional parameters, the description is adequate but leaves out details like whether at least one parameter is required, the output format, or any limitations. Annotations cover the safety profile, but the description doesn't address input requirements or result 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?

Schema coverage is 0%, so the description must explain the parameters. It does state 'por titular (CPF ou CNPJ)', which implies that either cpf or cnpj can be used to filter. However, it doesn't clarify whether they are mutually exclusive or how the search behaves when both are provided. It adds meaning beyond the bare 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 clearly states the tool lists trademarks registered at INPI filtered by holder (CPF/CNPJ). It distinguishes from siblings like consultas_marcas_busca and consultas_marcas_processo by specifying the 'by holder' scope.

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 use when you have a CPF or CNPJ to look up trademarks, but it does not explicitly state when to prefer this tool over alternatives like consultas_marcas_busca or consultas_marcas_processo. No exclusions or prerequisites are mentioned.

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 destructiveHint=false, so the safety profile is known. The description adds meaningful behavioral context: result limit ('até 100 processos') and returned fields (marca, número, classe, situação, titular). This goes beyond annotations, though pagination and exact matching behavior are not detailed.

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 just two sentences, front-loaded with the action and purpose, and contains no filler. Every phrase adds useful information: the target registry, the search mode, the result limit, and the returned fields.

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 selection, the description is sufficient: the tool's purpose, scope, and main output are clear. However, with six parameters, no schema descriptions, and no output schema, the lack of detail around optional filters and pagination leaves invocation gaps.

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%, and the description only clarifies the core search term ('pelo nome/termo'), likely mapping to the `marca` parameter. The other five parameters (`ncl`, `tipo`, `pagina`, `pedidos_vivos`, `pesquisa_textual`) are left unexplained, so the agent cannot infer their meaning or optional usage.

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 ('Busca') plus resource ('marcas no INPI') and clarifies scope ('pelo nome/termo'), with a clear output summary. It is distinguishable from consultas_marcas_processo, though it does not explicitly contrast itself with consultas_marcas or other siblings.

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

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

The description gives a concrete use case: checking whether a trademark name is already filed or registered ('Útil pra ver se um nome de marca já está depositado ou registrado'). It does not mention alternatives or when-not-to-use, so it stops short of a full guideline.

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, idempotentHint=true, and destructiveHint=false. The description adds meaningful context by enumerating exactly what information the tool returns, which is especially valuable because there is no output schema. It does not contradict any annotation.

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 one focused sentence that front-loads the main outcome ('Detalhes completos') and then uses a parenthetical list to convey scope without padding. Every part adds useful information, and there is no redundant restatement of the tool name or annotations.

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 a single-parameter read-only tool with no output schema, the description covers the required input and the product content well. It could be slightly more complete by noting the response format or any caveats around availability of data, but the described field list gives an agent enough information to decide whether this tool matches the user's request.

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?

There is no parameter-level description in the schema and schema description coverage is 0%. The tool description clarifies that numero_processo is an INPI trademark registration process number, but it does not add format guidance, expected normalization, or examples beyond what the parameter's name already suggests. It partially compensates for schema silence but not fully.

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 returns complete details of an INPI trademark registration process by process number, with a concrete list of included data areas (situação, depósito, concessão, vigência, titulares, classes, petições, publicações). This distinguishes it from siblings such as consultas_marcas or consultas_marcas_busca by focusing on full process-level details for a single process.

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 makes the usage context clear: use this when you have a specific processo number and need a comprehensive trademark-process dossier. It does not explicitly discuss alternatives or exclusions, but the 'pelo número do processo' phrasing gives a clear prerequisite and differentiates this from broader search-oriented 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?

The description is consistent with the annotations (readOnly, idempotent, non-destructive) but adds no additional behavioral details such as authentication requirements, rate limits, or potential side effects. Since the annotations already cover safety, the description contributes minimal extra transparency.

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 unnecessary words or repetition. It efficiently conveys the core 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?

The description is adequate for a simple lookup tool, but it lacks details about the output structure, what specific MEI data is returned, and the parameter constraints. Given the absence of an output schema, the agent has limited information about the expected response.

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 mentions that data is provided 'por CPF ou CNPJ', which indicates that either parameter can be used. However, it does not clarify whether one is required, if both can be provided simultaneously, or the expected format. The schema also has no required fields, leaving ambiguity.

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 that the tool retrieves MEI data by CPF or CNPJ, which is specific and unambiguous given the tool name and sibling context. However, it does not explicitly use a verb like 'consult' or 'retrieve', but the implication is strong.

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 guidance on when to use this tool versus the many sibling consultas_* tools. There is no mention of criteria like 'use when the entity is an MEI' or alternatives for other tax regimes. The choice is left to inference from the name alone.

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the specific input format (44-digit key), but does not describe return format, error handling, or any additional behavioral aspects like rate limits or authentication requirements. With annotations providing safety guarantees, a score of 3 is appropriate as it adds some but not rich context.

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 in Portuguese that directly conveys the tool's purpose and key parameter. It is front-loaded with the action and resource, and no unnecessary information is included. Perfectly efficient for its task.

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 simplicity (one parameter, no output schema, annotations covering safety), the description is adequate but leaves gaps: no mention of what is returned on success/failure, any validation requirements for the key, or whether there are restrictions on usage. For a simple lookup tool, this is acceptable but could be more 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 the description must compensate. It does: it specifies that the parameter is a chave de acesso with 44 digits, which adds meaning beyond the raw schema ('nfe': string). However, it does not specify whether the parameter is the full key or part, or how the key should be formatted. Since there is only one parameter and the description explains its semantics, a baseline of 3 is fair.

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: 'Consulta uma Nota Fiscal Eletrônica (NF-e) pela chave de acesso (44 dígitos).' It names the specific resource (NF-e), the action (consulta), and the key parameter (chave de acesso de 44 dígitos). This distinguishes it from sibling tools that query other types of data (e.g., consultas_cpf, consultas_fgts).

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 indicates that the tool is used when needing to query an NF-e, but it does not explicitly state when to prefer this tool over alternatives or any prerequisites (e.g., authorization, format validation). The sibling list shows many similar consultas_* tools, but the description does not clarify how to choose among them beyond the specific resource type.

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?

As anotações já cobrem readOnlyHint, idempotentHint e destructiveHint, então a carga comportamental é menor. A descrição adiciona o objeto da busca e o critério nome/termo, mas não detalha formato de retorno, paginação ou limites; ainda assim, é suficiente para uma consulta simples e não contradiz as anotações.

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 descrição é uma frase única, direta e sem conteúdo redundante. A informação essencial aparece já no início, sem encher linguiça.

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?

A ferramenta é simples: um parâmetro obrigatório, anotações de segurança claras e uma descrição que identifica a base e o tipo de consulta. A ausência de output schema não é um problema relevante aqui, pois o nível de complexidade é baixo e a descrição cobre o necessário.

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?

O schema apenas define 'query' como string, sem explicação semântica. A descrição compensa ao dizer que a busca é 'por nome/termo', o que dá significado suficiente ao único parâmetro obrigatório.

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?

A descrição usa verbo específico 'Busca' + recurso concreto 'base ICIJ Offshore Leaks (paraísos fiscais)', deixando claro o escopo da ferramenta. Isso a diferencia dos demais tools de consulta irmãos, que apontam para outras bases (CPF, FGTS, sanções etc.).

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?

A descrição fornece contexto claro de uso: pesquisar nomes/termos na base Offshore Leaks relacionada a paraísos fiscais. Não menciona alternativas ou exclusões explícitas, mas a especificidade da base permite que o agente escolha esta ferramenta entre as demais consultas.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds the source (INPI) and the holder-based filtering, but does not disclose any further behavioral traits such as rate limits, pagination, or response structure. Given the annotations, this is adequate but not rich.

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 information. It is front-loaded and concise, containing all essential purpose 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?

Given the tool's simplicity (no output schema, only two optional params), the description is concise but lacks detail on what the response contains (e.g., list of patent numbers, dates). While it covers the basic purpose, it does not fully contextualize the expected behavior or results, which would be helpful for a comprehensive tool description.

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%, so the description must compensate. It states that the holder is identified by CPF or CNPJ, giving purpose to both parameters. However, it does not clarify whether both can be provided together, if one is required, or any format requirements. This provides minimal added meaning beyond the bare 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 clearly states the tool's function: retrieving patents registered at INPI by holder (CPF or CNPJ). It uses a specific verb and resource, and distinguishes itself from sibling tools like consultas_marcas (trademarks) by focusing on patents.

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 guidance on when to use this tool versus other sibling tools (e.g., consultas_marcas, consultas_cpf). There is no mention of alternatives, exclusions, or prerequisites, leaving the agent to infer usage solely from the purpose.

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?

As anotações já declaram readOnlyHint=true, idempotentHint=true e destructiveHint=false, então o agente sabe que é uma leitura segura. A descrição não adiciona detalhes comportamentais além disso, como formato de retorno ou se há correspondência parcial; com anotações presentes, o valor adicional é mínimo mas não contraditório.

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?

Uma única frase que contém verbo, objeto e complemento, sem redundância ou palavras supérfluas. É direta e de fácil leitura.

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?

A ferramenta é simples (um parâmetro string, sem output schema) e as anotações cobrem a segurança da operação. A descrição é suficiente para entender a função principal, embora não indique o que exatamente é retornado (ex.: lista de correspondências, detalhes da sanção), o que poderia ser útil mas não é obrigatório dado o nível de complexidade.

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?

A cobertura do schema é 0%, então a descrição precisa compensar. Ela indica que o parâmetro 'query' é usado para buscar 'por nome/termo', dando semântica à string que o schema não fornece. Ainda assim, seria útil especificar formato ou limitações do termo, mas para um único parâmetro simples é suficiente.

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?

A descrição usa verbo específico 'Busca' e identifica claramente o recurso: 'listas de sanções do OFAC (EUA) por nome/termo'. Isso diferencia de ferramentas irmãs como consultas_sancoes_onu, ao especificar a jurisdição (EUA).

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?

Não há orientação explícita sobre quando usar em vez de alternativas nem exclusões. O contexto é implícito: o nome OFAC (EUA) sugere uso para sanções americanas, mas não há menção a ferramentas alternativas como consultas_sancoes_onu ou critérios de escolha.

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, idempotentHint, and non-destructive behavior, covering the core transparency needs. The description adds no extra behavioral context, such as pagination or result limits, but does not contradict 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 is front-loaded and directly addresses the tool's function. It contains no fluff and 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?

For a simple read-only search tool with one parameter and no output schema, the description and annotations together provide adequate context. It lacks minor details like case sensitivity or output structure, but these are not essential for an agent to invoke the tool correctly.

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

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

The sole parameter 'query' has zero schema description coverage. The description compensates by indicating the query is a 'nome/termo' (name/term), providing essential meaning for what to pass. Although no format examples are given, the single-sentence clarification is sufficient for a basic search.

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 searches UN sanctions lists by name/term, using a specific verb ('Busca') and resource ('listas de sanções da ONU'). It distinguishes itself from sibling tool 'consultas_sancoes_ofac' by specifying the UN context.

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 UN sanctions searches but does not explicitly mention when to use this versus alternatives like OFAC. No exclusions or contextual cues beyond the resource name 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?

The annotations already declare read-only, idempotent, and non-destructive behavior. The description adds useful behavioral context by disclosing that only the first process has its details and movements returned, which is material to the caller.

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 concise: one sentence for what is searched, one for the return structure, and one for the required input condition. No wasted words, and the most actionable guidance is preserved.

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?

Even without an output schema, the description explains the main return pieces: class, distribution, parties, general information, and movements. It also covers the at-least-one-identifier rule. It could mention the role of 'nome_mae' or what happens when no process is found, but overall it is informative enough.

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. It does explain that CPF, CNPJ, name, and process number are accepted identifiers and that at least one is needed. However, it omits the 'nome_mae' parameter and gives no format, combination, or precedence rules, leaving some ambiguity.

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 that the tool searches criminal execution processes in SEEU by CPF, CNPJ, party name, or process number. It also specifies what is returned: found processes plus details of the first match, which distinguishes it from the other consultas_* siblings.

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

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

It gives an explicit usage rule: inform at least one identifier. It also lists valid query identifiers, which is helpful. It does not explicitly compare against alternatives, but the SEEU-specific execution-process context is clear enough for an agent to know when this tool is relevant.

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 idempotentHint=true, covering the operational safety profile. The description adds no further behavioral details, such as error handling, output format, or potential side effects, but does not contradict 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, concise sentence that front-loads the key purpose without extraneous detail, earning full marks.

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 (one parameter, no output schema), but the description is minimal. It does not outline what 'situação' entails (e.g., status string, full registration details), leaving the agent to infer the response 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?

With zero schema description coverage, the description compensates by explicitly mentioning 'CNPJ', clarifying that the single 'cnpj' parameter refers to the tax ID. It does not, however, specify format or validation rules (e.g., digits only, masks).

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: it retrieves the Simples Nacional / SIMEI status for a CNPJ. This is specific and distinguishes it from sibling tools targeting other data domains (e.g., CPF, FGTS, federal debits).

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 name and description imply usage for Simples Nacional status queries, but there is no explicit guidance on when to prefer this tool over alternatives or exclusions. The context is implied, not 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?

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description does not contradict them. It adds the context that this is a SINTEGRA registration-status lookup, but it does not disclose runtime behavior such as authentication needs, invalid input behavior, or what exact statuses are returned.

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 puts the key information upfront: domain, state, and input type. It contains no filler and every word contributes meaning.

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 query tool with two simple string parameters and good annotations, the description is mostly sufficient: it names the purpose, the geographic scope, and the supported identifiers. There is no output schema and the response structure is not described, so it is not fully complete for an unfamiliar caller.

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 0%, so the description carries the burden of explaining the parameters. It only repeats the property names by saying 'por CNPJ ou CPF' and does not clarify formats, constraints, or whether at least one identifier is required; the schema marks both as optional, leaving ambiguity.

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 identifies the resource: ICMS SINTEGRA registration status for the state of RJ, queried by CNPJ or CPF. It distinguishes itself from SINTEGRA sibling tools by the explicit 'estado do RJ' scope, though it lacks a direct verb such as 'consulta' or 'obtém'.

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 scope 'no estado do RJ' and the query parameters 'por CNPJ ou CPF' imply when the tool is useful, and the sibling names suggest state-based alternatives. However, the description does not explicitly say when not to use it, mention alternatives by name, or list prerequisites.

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, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read operation. The description adds the specific data source (SINTEGRA) and the state (SP), which is useful context. However, it doesn't disclose any additional behavioral traits like rate limits, authentication requirements, or what happens if both CPF and CNPJ are provided. With annotations covering the safety profile, a 3 is appropriate.

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 conveys the core purpose. It's front-loaded with the key information (SINTEGRA, SP, CNPJ/CPF). No wasted words. However, it could be slightly more structured by mentioning the read-only nature, but that's already in annotations.

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 simplicity (2 optional parameters, no output schema, no nested objects), the description is mostly complete. It covers the purpose and the input parameters. However, it doesn't mention what the output looks like (since there's no output schema), nor does it clarify whether both CPF and CNPJ can be used together or if one is preferred. For a simple query tool, this is adequate but not exhaustive.

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. The description mentions 'por CNPJ ou CPF', which indicates that either parameter can be used, but it doesn't explain the format, validation rules, or whether both can be provided simultaneously. The schema only defines the parameters as strings with no additional constraints. The description adds minimal value beyond the schema, so a baseline 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 purpose: it retrieves ICMS registration status (SINTEGRA) for the state of SP, using CNPJ or CPF. It specifies the resource (SINTEGRA registration) and the scope (SP state), which distinguishes it from sibling tools like consultas_sintegra_rj and consultas_sintegra_suframa. However, it doesn't explicitly mention that it's a read-only query, but that's covered by annotations.

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: it's for checking ICMS registration status in SP. It doesn't explicitly state when to use this tool versus alternatives, but the state-specific scope (SP) and the mention of CNPJ/CPF provide some context. No exclusions or alternatives are mentioned, but the sibling tools for other states (RJ, SUFRAMA) are implicitly differentiated by the state name in the description.

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 destructiveHint=false, establishing a safe read operation. The description adds that the tool queries by CNPJ or CPF, which is useful but not a behavioral trait beyond what the schema and annotations imply. It does not mention rate limits, auth requirements, or potential variations in response, but with the annotations covering safety, this is acceptable.

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 conveys the tool's purpose. There is no redundant wording, and the key information—agency and identifier types—is front-loaded and efficient.

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 lookup tool, the description is sufficient to understand its scope and distinguish it from siblings. There is no output schema, but the description does not need to detail return values for such a straightforward query. It covers the essential context (SUFRAMA, CNPJ/CPF) and aligns with the tool's simplicity.

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 has no descriptions for 'cpf' and 'cnpj' (coverage 0%), so the description must compensate. It does indicate that the tool works by CNPJ or CPF, giving some meaning to the parameters. However, it does not clarify whether both can be provided, if one is sufficient, or any expected format, leaving ambiguity for the agent.

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: providing the registration status at SUFRAMA, a specific Brazilian agency, using either CNPJ or CPF. It uses a specific verb (consultas/consults) and resource (SUFRAMA), and it distinguishes itself from sibling tools like consultas_cpf and consultas_sintegra_sp by naming the agency.

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 gives no explicit guidance on when to use this tool versus other alternatives. It only states what it does, without mentioning prerequisites, exclusions, or comparisons to similar tools like consultas_sintegra_rj. The context of the name suggests it is for SUFRAMA, but the description itself offers no usage direction.

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?

As anotações (readOnlyHint, idempotentHint, destructiveHint) já declaram o caráter não destrutivo e idempotente. A descrição acrescenta contexto sobre o conteúdo retornado (categorias de penalidades), mas não detalha comportamentos adicionais como autenticação ou limitações.

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?

Frase única e objetiva, sem redundâncias, entrega as informações essenciais de forma direta e eficiente.

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?

Para uma ferramenta com um único parâmetro, sem schema de saída, a descrição fornece contexto suficiente sobre o que consulta e quais informações estão inclusas. Faltam detalhes como formato de resposta ou data de referência, mas é adequada para o nível de complexidade.

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?

O schema tem apenas o parâmetro 'cnpj' sem descrição. A descrição compensa ao mencionar 'por CNPJ', esclarecendo o propósito do parâmetro, embora não forneça detalhes extras como formato esperado.

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?

A descrição especifica claramente o verbo 'Consulta' e o recurso 'TCU para uma PJ', detalhando o escopo (inidôneos, inabilitados, contas irregulares) e o identificador (CNPJ). Diferencia-se dos irmãos ao focar exclusivamente no TCU.

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?

A descrição indica implicitamente o uso para consultar dados consolidados do TCU por CNPJ, mas não oferece orientação explícita sobre quando usá-la em vez de outras ferramentas, nem menciona pré-requisitos ou alternativas.

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 only provide generic hints (readOnlyHint=false, openWorldHint=true). The description carries the full burden and does so richly: it explains that invoke runs MCPs one-off without installing, that it returns connect/checkout links when credentials or payment are needed, that writes require owner/admin rights, and distinguishes the prompt library. No contradiction with 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 dense paragraph that covers an enormous amount of ground without any hierarchical structure (no bullet points, headers, or separation of the prompt library from the MCP marketplace). While every sentence contains useful information, the lack of structure makes it harder to absorb, and it is arguably too long for a tool description. It is information-dense but not well-scaffolded.

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 complexity (14 distinct actions, 23 params, no output schema), the description covers the key workflows, auth, payment, and the prompt library. It does not detail every parameter or return payload, but it provides enough operational context for an agent to use the tool effectively. The lack of output schema is offset by describing what happens (e.g., invoke returns connect/checkout links).

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. It does explain the critical action parameter and ties it to the flow (search, describe, invoke, install, etc.), and implicitly covers mcp_id, tool_id, arguments, and prompt_* fields. However, many parameters (limit, query, immediate, tier_slug, cancel_reason, prompt_targets, etc.) remain undocumented, and the description does not explicitly map all 23 parameters even at a high level.

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 a precise definition: "The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them." It clearly distinguishes this from sibling tools (specific consulta tools) and enumerates the core functions (search, describe, invoke). It is a specific verb+resource description with clear scope.

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 gives explicit when-to-use guidance: "prefer invoke for a single/occasional use" vs "Use install only to make an MCP PERMANENT". It also states when to use search/describe vs list_tools, and explains when subscribe/cancel, report_bug, request_mcp are appropriate. This directly guides selection among numerous actions.

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?

The annotations already mark the tool as non-read-only and idempotent, and the description adds that the conversation array should be attached for reproduction. However, it does not disclose what happens after submission, whether data is sent externally, or what the response/outcome will be. No contradiction with 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 concise sentences that front-load the main purpose and then provide one crucial usage detail. There is no wasted wording or redundant restating of the title.

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 reporting tool, the description covers the main action and one important input behavior, but leaves the 'context' parameter unexplained and provides no information about the response format or side effects. The lack of annotations and output schema increases the burden, making this only minimally 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?

With 0% schema description coverage, the description needed to explain all parameters, but it only covers the 'conversation' array and implicitly the 'message' field. The 'context' parameter is completely unexplained, and the schema provides no descriptions, leaving a significant gap.

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 identifies the tool's purpose: reporting bugs, missing features, or feedback. It uses a specific verb with a resource and is distinct from the sibling tools, which are mostly query/consultation operations.

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 gives clear usage context: use this when the user wants to report a bug or provide feedback. It also instructs the agent to include the conversation array for reproduction. It does not explicitly mention when not to use it, but the context is unambiguous enough.

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, idempotentHint=true, and destructiveHint=false. The description adds no extra behavioral context beyond restating that it shows versions, which is consistent with the annotations. It does not disclose potential error conditions or the exact format of the response, but with annotations covering the safety profile, a moderate score is appropriate.

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 states the exact purpose with no filler words. It is front-loaded and 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?

For a simple, zero-parameter read-only tool with annotations and no output schema, the description fully captures the tool's scope. There is no missing information that an agent would need 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 tool has zero parameters, so the schema fully covers them by default. The description does not need to add parameter semantics, and the baseline of 4 for zero parameters 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 'Show' and clearly identifies the resource: 'the current MCP platform and adapter versions.' It distinguishes itself from all sibling tools, which are primarily consultation or authentication tools, by being the only one that displays version information.

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 of the tool is self-evident: to display version information. This gives clear context for when to use it, though it does not explicitly state when not to use it or mention alternatives like toolkit_info.

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, idempotentHint=true, and destructiveHint=false. The description adds value by enumerating the exact content returned (installed MCPs, connection status, accounts, catalog tool counts), which goes beyond the annotation safety profile without contradicting it.

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 stating the primary purpose first, then listing specific data points. Every word adds value; no filler or 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?

With no output schema, the description sufficiently conveys the tool's return content (MCP states, connections, accounts, catalog counts). While it doesn't specify a structural format (e.g., JSON object), the nature of the tool is straightforward and the listed components give an agent enough context to invoke and interpret the result.

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

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

The tool has zero parameters, so schema coverage is trivially complete. Per rubric, a baseline of 4 applies to zero-parameter tools; the description correctly omits any parameter details since none exist.

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 returns the current toolkit state with specifics (installed MCPs, connection status, accounts, catalog tool counts). It uses a specific verb 'returns' and distinguishes this meta-tool from the numerous consultas_* query tools and authentication 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?

The description implies the tool is for checking toolkit state, which is clear from context. It doesn't explicitly mention alternatives or when not to use it, but given its unique purpose among siblings (all others are domain-specific or action tools), the usage context is clear.

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