radar-cnpj

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 a quota limit and the error code 402, which is a meaningful behavioral trait. However, it does not explain success response, idempotency, or whether an existing watch gets replaced. For a simple add operation, the quota disclosure is valuable but incomplete.

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 with no waste. The primary action is front-loaded, and the quota note is appended efficiently. It is well-structured and easy to parse.

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 covers the core action and a key quota behavior, but it omits details about the success response and does not mention any prerequisites or side effects beyond quota. Given the tool's simplicity, the missing return information is a minor gap, but it is not fully complete for an agent to predict the outcome.

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 50% (only cnpj has a description). The description adds no parameter semantics beyond what the schema already provides; it does not explain session_id or elaborate on formatting requirements. It fails to compensate for the undocumented parameter.

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 'Adiciona' (adds) and the resource 'CNPJ aos watches da sessão' (CNPJ to the session's watches). It distinguishes from siblings like list_watches (list) and get_cnpj (get) by specifying the action of adding to the session. The scope is explicit and unambiguous.

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 quota constraint ('first 10 free, then 402') that implicitly guides usage, but it does not explicitly state when to use this tool over alternatives or mention exclusions. It lacks a contrast with sibling tools or conditions for when not to use it, so the guidance is only partially present.

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

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

With no annotations, the description carries the full behavioral burden. 'Índice' implies a read-only listing operation, but the description does not state what the index contains, whether authentication is needed, or whether any side effects exist.

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 short sentence with no waste and front-loads the resource and domain. It is appropriately concise, though it borders on under-specification.

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 has no annotations and no output schema, so the description should explain what the index contains and what invoking it returns. It does neither, leaving an agent to guess at response format and usage.

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 and schema coverage is 100%, so there is no parameter information the description needs to supply. This matches the baseline for a parameterless 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 identifies the resource as an index of the Radar CNPJ API, so an agent can infer it provides an overview/catalogue. However, it is a noun phrase rather than a verb+resource action, and it does not differentiate it from sibling tools such as ref or health.

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

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

There is no guidance on when to use this tool versus alternatives. It gives no context, exclusions, or alternatives, despite the sibling tool list being available.

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 disclosure burden. It discloses the core evaluation logic and the HTTP method (POST /api/avaliar), plus the negative behavior (no Google search estimation). But it does not mention return format, auth requirements, or side effects of the POST call.

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

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

Three concise sentences with no filler: the main action, the key limitation, and the endpoint. 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?

The description covers the tool's core purpose and key limitation, but with no output schema and no annotations, it leaves gaps around the exact response shape, failure modes, and whether callers need any authentication. The formula hints at the output (count of active businesses) but doesn't confirm it explicitly.

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%, so the baseline is 3. The description reinforces the relationship between parameters via the 'CNAE + lugar → contagem de ativas' formula, but it doesn't add detail about the hint parameters (uf, municipio) 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 states a specific verb and resource: 'Avalia uma ideia de negócio contra a base da Receita' and even defines the evaluation formula ('CNAE + lugar → contagem de ativas'). The negation 'Não estima busca no Google' explicitly differentiates it from search-related 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 clear context for use (evaluating a business idea against the Receita database) and an explicit when-not ('Não estima busca no Google'). However, it doesn't name an alternative sibling that would handle Google search estimation, stopping short of full routing 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?

There are no annotations, so the description must carry the full burden of behavioral disclosure. It does mention a 402 payment requirement and a 429 rate limit with Retry-After, which are useful operational details. However, these are cryptic and not clearly explained (e.g., what does 'x402' mean?). It adds some behavioral context but falls short of being transparent about the tool's core 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 extremely terse, but it sacrifices clarity for brevity. It is a single cryptic sentence with ambiguous symbols and lacks a clear structure. The purpose is not front-loaded, and the error information is presented without context. This is not effective conciseness; it's under-specification.

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 four required parameters and no output schema, the description should explain what the tool accomplishes and what to expect in return. It only provides error hints and no context about the contact action itself. The agent would struggle to know when to call this tool and what a successful call returns. The description is severely incomplete.

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 provides descriptions for all four parameters (nome, email, mensagem, aberto_em) with 100% coverage. The tool description does not add any additional semantic meaning beyond what the schema already states. Baseline of 3 is appropriate since the schema handles the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Contato' is a repetition of the tool name in Portuguese, providing no verb or resource. It does not state what action the tool performs, leaving the agent to infer from the parameter names. This is a tautology and fails to differentiate from sibling tools like 'suggest' or 'avaliar'.

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 offers no guidance on when to use this tool versus alternatives. It only mentions error codes and rate limits, which is unrelated to usage context. There is no mention of scenarios, prerequisites, 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?

With no annotations, the description carries the full burden. It indicates a read-oriented retrieval operation ('Ficha de empresa') but does not disclose return format, error behavior, authorization needs, or whether the CNPJ is validated beyond digit count. For a simple getter, this is minimally 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 short phrase with no redundant words. It is front-loaded with the core purpose. Very concise, though slightly information-sparse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter lookup tool with no output schema, the description is enough to understand basic intent, but it does not explain what fields the returned 'ficha' contains or what happens on invalid input. Given the tool's simplicity, this is acceptable but not comprehensive.

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

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

Schema description coverage is 100%, and the parameter is already described as '14 dígitos' in the schema. The description adds no new semantic detail beyond reinforcing the exact-number requirement, 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 identifies the resource (company record, 'Ficha de empresa') and the lookup criterion (CNPJ). It is unambiguous and does not repeat the tool name. However, it lacks an explicit verb and does not directly differentiate itself from sibling tools like search or suggest.

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 rather than stated: 'por CNPJ (14 dígitos)' suggests this is for exact CNPJ lookup as opposed to search or suggestion tools. There is no explicit when-to-use or when-not-to-use guidance, but the 14-digit requirement gives a practical hint.

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 behavioral disclosure and 'Health da base' does not disclose any behavior. It does not state whether the operation is read-only, what it returns, whether side effects are possible, or what 'health' means in this 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 very brief, at four words, but this is under-specification rather than effective conciseness. It gives a noun phrase with no action, behavior, or expected output, so the brevity does not adequately support an agent.

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 in terms of inputs, but there is no output schema and no annotations, so the description must explain what the tool does and what the agent should expect. 'Health da base' leaves both the operation and return value undefined, so the description is not complete 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?

The tool has zero parameters and an empty input schema, so there are no parameter semantics to document. The description does not add parameter-level detail, but none is required; this is the appropriate baseline for a parameterless 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 'Health da base' identifies the resource as the database/base and implies a health-check intent, but it lacks a verb that explicitly states what the tool does. It is less ambiguous than a pure tautology because 'da base' scopes the resource, yet it does not clarify whether the tool checks, returns, or monitors health.

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

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

There is no guidance about when to use this tool versus its siblings. The description does not name alternatives, conditions, or exclusions, so an agent cannot determine how to choose between this and tools like list_watches or get_cnpj.

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?

Sem anotações, a descrição carrega todo o peso da transparência. Ela apenas afirma a conversão, sem mencionar efeitos colaterais, idempotência, autenticação ou o formato do resultado. Um agente não sabe se a operação é de leitura ou escrita, nem o que retorna.

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 extremamente concisa, com uma única frase que entrega a ação principal e o endpoint. É bem estruturada e não contém palavras desnecessárias, embora seja tão curta que pode ser subespecificada.

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 parâmetro e sem schema de saída, a descrição deveria explicar o que o agente recebe de volta ou como interpretar os filtros. Nada disso é mencionado, deixando o agente sem informação crucial para o uso correto.

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 cobre 100% do parâmetro texto, então a descrição não precisa detalhá-lo. No entanto, não adiciona nenhuma nuance além do que o schema já diz, como exemplos ou restrições de formato.

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 indica claramente uma ação específica: converter texto natural em filtros, com o endpoint POST /api/ia. Isso diferencia de ferramentas como search ou suggest, mas não detalha o tipo de filtro ou o contexto de uso.

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 nenhuma orientação sobre quando usar esta ferramenta em comparação com as ferramentas irmãs (search, suggest, list_watches, etc.). Não menciona cenários de uso nem quando não usar.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It establishes that this is a read/list operation, but it does not describe return format, behavior for invalid or missing sessions, ordering, pagination, or empty results. This is too thin for an agent to predict behavior confidently.

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 very short, front-loaded, and free of filler. It captures the core operation efficiently, but it is so minimal that it omits useful behavioral context, which prevents a perfect score.

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 annotations, a one-phrase description is not complete. It does not explain what the tool returns, whether it can fail, or how errors are surfaced, leaving material gaps for an agent trying 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 phrase 'da sessão' adds some meaning by tying session_id to the session whose watches are being listed. However, schema description coverage is 0%, and the description does not clarify ID format, session state requirements, or ownership constraints, so it only partially compensates for the missing schema 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 uses a specific verb 'Lista' and names the resource 'watches', scoped to 'da sessão'. It clearly communicates that this tool lists watches for a given session, and the sibling tool add_watch provides a natural contrast even without an explicit distinction.

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 given about when to use this tool versus alternatives like add_watch or monitor_session. The intended use case is only implied by the verb 'Lista', leaving the agent to infer when this is the right choice.

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. It only states that city/state information for the visitor is returned, but does not clarify the meaning of 'borda', whether this is a safe read operation, or any other behavioral constraints.

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 short and contains no filler words, which is a form of conciseness. However, it is so terse that key context such as 'borda' is left undefined, so brevity comes at the cost of clarity.

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 zero-parameter tool, the description at least names the expected output domain (city/UF), but without an output schema, annotations, or explanation of 'borda', the agent still lacks important context about what this tool actually returns and how it behaves.

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 and the schema is empty, so there are no parameter semantics to explain. The baseline of 4 for a zero-parameter tool is appropriate because this dimension is trivially satisfied.

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 identifies the resource and output fields ('visitor' and 'city/UF'), which prevents a pure tautology from the tool name 'local'. However, it lacks an explicit verb and the term 'borda' is ambiguous, leaving the tool's exact purpose unclear.

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 guidance on when to use this tool versus its siblings such as search, ia_filters, or get_cnpj. An agent would have to infer that this is a geolocation lookup from the name and the 'cidade/UF' reference.

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

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

With no annotations, the description carries the full behavioral burden. It discloses only the basic action and anonymity, but omits side effects, session lifecycle, return behavior, or any auth or runtime requirements.

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 filler and the action is front-loaded. It is appropriately sized for a zero-parameter tool.

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?

There is no output schema and the description does not mention what the session creation returns or how the caller should use it. For a stateful operation, this leaves important context missing.

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

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

The parameter count is zero, so the baseline is 4. The input schema is empty, and the description does not need to explain parameter details because there are none.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Cria sessão anônima de monitoramento.' This communicates the core action clearly, though it does not explicitly differentiate the tool from siblings such as add_watch or list_atches.

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 usage guidance is provided. The description does not say when this tool should be used, whether it is a prerequisite for other monitoring tools, or how it compares to sibling tools.

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. It says nothing about side effects, read-only vs. mutating nature, authentication requirements, rate limits, or return format. For a tool with no annotations, this is a critical 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 extremely short, but it is under-specified rather than concise. It consists of a single noun phrase with no verb or action. While it is front-loaded, it omits essential information, so it does not earn the conciseness score.

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 2 parameters, no output schema, and no annotations, the description must provide substantial context. It fails to explain what the tool returns, how results are formatted, or what 'ref' implies. An agent cannot reliably call this tool based on the current 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 description coverage is 100% – both 'q' and 'tipo' have descriptions in the schema. The description adds no extra meaning beyond the schema; it merely restates the enum values. Baseline 3 is appropriate because the schema already documents parameters, but the description provides no supplementary value.

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 'Ref CNAE/município/natureza' is a noun phrase with no verb or explicit action. It lists resource types (CNAE, município, natureza) but does not state what the tool does with them (e.g., look up, reference, or suggest). It provides no differentiation from sibling tools like 'search' or 'suggest', leaving an agent unable to determine the tool's function.

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 indication of when to use this tool versus the 12 siblings. No context on appropriate scenarios, prerequisites, or exclusions is provided. An agent has no guidance to decide between 'ref' and 'search' or 'suggest'.

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. It only states the action of searching companies, without mentioning read-only nature, pagination, response format, or any side effects. This is insufficient for a search tool with 5 parameters.

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, short sentence that front-loads the action ('Busca empresas') and immediately mentions the main parameters. There is no wasted wording, and the structure is optimally concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 parameters, no output schema, and no annotations, the description is far too brief. It fails to explain pagination usage, response structure, or any practical details needed for correct invocation. The agent is left without context on how to handle results or edge cases.

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

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

Schema coverage is 100%, with each parameter already described. The description adds a small note that q and/or filters (f=JSON) can be used, which is a minor clarification beyond the schema. However, it does not explain syntax or how parameters interact, so it remains at the baseline.

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?

Description clearly states 'Busca empresas' (search companies), specifying the verb and resource. It also mentions the key parameters q and f, but does not distinguish this from sibling tools like suggest or get_cnpj, leaving some ambiguity in tool selection.

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 siblings. There is no mention of exclusions, prerequisites, or conditions that would steer an agent toward or away from this tool. The description only states what it does, not when to use it.

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

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

No information is given about side effects, read-only nature, or what the tool actually returns. The description does not disclose whether it is safe or if it modifies any state.

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 short, which makes it concise but also under-specified. While it is front-loaded with the only information, the brevity comes at the cost of clarity and usefulness.

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 lacks an output schema and any details about the return value or use case. With only the name and minimal parameter info, the description is incomplete and does not enable a caller to understand 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 parameter 'q' has a description in Portuguese ('O que já foi digitado') clarifying it is the user's typed input. However, it lacks format, examples, or constraints, providing only basic meaning.

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 'Autocomplete.' is vague, not specifying the resource, context, or type of suggestions. It names the feature but lacks a clear verb phrase or object, making the tool's exact purpose ambiguous.

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 like 'search' or 'list_watches'. There is no context about the appropriate scenario for calling 'suggest'.

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