scrypta-mcp

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 conveys only that a price is looked up, saying nothing about read-only safety, authentication/tenant requirements via cnpj, error behavior for unknown products, or rate limits. 'Consulta' weakly implies a read, but that is inference, not disclosure.

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

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

A single front-loaded sentence with no filler, which is appropriate for a simple lookup. Brevity is not the problem here; the omitted content is.

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?

An output schema exists, so return values need not be explained, but two required parameters and the required cnpj tenant context go entirely unaddressed while the description references parameters that do not exist. For a two-required-parameter tool with zero schema descriptions and no annotations, this is materially 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?

Schema description coverage is 0% and both required parameters (cnpj, product_id) are left undocumented. Worse, the description describes lookups by 'índice (numérico)' or 'nome', neither of which matches a schema parameter, and it never mentions cnpj at all. Rather than compensating for the coverage gap, it points the agent at the wrong inputs.

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

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

States a clear verb and resource: 'Consulta o preço de um produto' (query a product's price). It implies a lookup tool distinct from list_products or get_company_details, but never names a sibling or scoping condition to draw the boundary. The identification modes it lists ('índice' or 'nome') are also not the ones the schema requires, muddying what the tool actually operates on.

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 on when to use this tool versus list_products, get_company_details, or search_companies. Nothing about prerequisites (a valid cnpj, an existing product) or when-not to call it. The agent must infer usage entirely from the name.

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 discloses real behavior: an LLM cascade with automatic fallback, enrichment sourced from the official website, and cache return on already-enriched records (implying idempotency and cost/latency). It does not state whether enrichment persists/overwrites data, permission requirements, or latency expectations.

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 tight sentences, front-loaded with the core action and source, then the caching behavior. No filler or repetition.

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?

An output schema exists, so return-value explanation is not needed. However, for an AI-driven enrichment operation with no annotations, the description omits persistence side effects, permissions, and cost/latency implications an agent would want before invoking it.

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

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

Schema coverage is 0% and the single required cnpj parameter is undocumented in both schema and description. 'a partir do site oficial' hints that the CNPJ drives an official-website lookup, but format and validation are left to inference; with only one obvious identifier this is partially compensated.

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

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

States a specific verb (enrich) and resource (company dossier) plus the mechanism (AI/LLM cascade) and data source (official website). An agent can distinguish it from read-only siblings like get_company_details or search_companies, though no sibling is named explicitly.

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

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

Implied usage only: call it when a company dossier needs AI enrichment. The note that it returns the cache if already enriched gives useful context about repeat calls, but there is no explicit when-to-use-versus-alternatives guidance relative to get_company_details.

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

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

No annotations are provided, so the description carries the full burden. It hints the data is 'público' (public), which weakly signals a read-only, non-sensitive operation, but it says nothing about authentication, rate limits, accuracy/freshness of registry data, or error behavior for invalid CNPJs.

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

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

A single front-loaded sentence with zero filler: verb first, then resource, then input constraint. Nothing redundant or padded.

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

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

For a simple one-parameter lookup with an output schema present, the definition covers the essential input format and the nature of the result, so return values need not be explained. The remaining gap is routing guidance against enrich_company_ai/search_companies, which is minor given the distinct CNPJ-based semantics.

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% — the schema only declares 'cnpj' as a bare string. The description compensates by giving the critical format constraint (14 digits), which is exactly the information an agent needs to invoke correctly. It does not cover edge cases like formatted vs unformatted input.

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

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

States a specific verb and resource: 'Retorna o dossiê público de uma empresa brasileira' — an agent knows it fetches a full company dossier rather than a list or a search result. The 'a partir do CNPJ' clause shows it is an identifier-keyed lookup, implicitly distinguishing it from list_companies/search_companies, though no sibling is named explicitly.

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

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

The required CNPJ key implies the use case (you already have a company identifier and want its full record), but there is no explicit when-to-use/when-not guidance and no mention of alternatives such as enrich_company_ai or search_companies. Usage is only implied.

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 behavioral burden, and it does disclose one meaningful constraint: results are limited to Verified-plan companies, and ostensibly only 'visible' contacts. It says nothing about authentication, failure modes when the company is not Verified, or result limits.

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

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

A single front-loaded sentence with no filler — the resource and its key restriction are stated immediately. 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?

An output schema exists, so return values need not be explained, and the plan restriction is noted. However, the only input parameter is undocumented and no error or eligibility behavior is described, leaving gaps for a tool whose main gate is plan-based.

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 sole required parameter (cnpj) has no prose description in either the schema or the description. 'de uma empresa' only weakly implies the parameter identifies a company; format and expected value are left entirely undocumented.

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 ('Retorna os contatos visíveis de uma empresa'), making it clear this is a read operation returning contact records. It does not, however, distinguish itself from siblings like get_company_details or list_companies, which an agent must infer.

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 names a gating condition — 'apenas plano Verified' — which tells the agent when the call will succeed. Beyond that, there is no guidance on when to prefer this over get_company_details or other lookup 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?

No annotations are provided, so the description carries the full behavioral burden. It does disclose one useful constraint (max 50 results), but says nothing about ordering, permissions, pagination, or what happens when the data set exceeds the cap.

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

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

A single short sentence with no filler, and the scope constraint is front-loaded. It is efficient, though its brevity leaves several questions unanswered.

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?

An output schema exists, so return values need not be described, but with no annotations, no parameter documentation, and no usage guidance, the definition is under-specified for a tool that competes with search_companies and get_company_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 coverage is 0% and the single parameter 'limit' has no description or default documented in the schema. The description only hints at a hard cap of 50, without tying it to the limit parameter or clarifying its default of 10.

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

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

States a specific verb ('Lista') and resource ('empresas armazenadas no Scrypta') with a scope qualifier ('últimas') and a cap. It distinguishes itself from search_companies by implying a recency-based default listing, though it never names the alternative.

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

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

There is no explicit guidance on when to use this tool versus search_companies or get_company_details. 'Últimas' hints at a recent-companies listing, but the agent is left to infer the selection criteria.

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

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

No annotations are provided, so the description carries full behavioral burden. It hints at the data source (the company dossier) but says nothing about permissions, behavior for un-enriched companies, pagination, or whether the list can be empty. That leaves meaningful behavioral gaps for a data-extraction tool.

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

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

A single front-loaded sentence with the action and resource up front and no filler. It is efficient, though extremely short given the tool's undocumented parameter.

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?

An output schema exists, so return values need not be explained. However, with no annotations and an undocumented required parameter, the description leaves gaps around prerequisites (enrichment state) and the meaning of the cnpj input that an agent would need to call 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?

Schema description coverage is 0%, so the single 'cnpj' parameter is undocumented in both schema and description. The phrase 'de uma empresa' only loosely implies cnpj identifies the company, and no format or validity information is given, leaving the required parameter under-specified.

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 ('Lista') and resource ('os produtos/serviços') and scopes it to a company's dossier, which distinguishes it from company-listing siblings like list_companies and search_companies. It is clear, though it never explicitly names an alternative tool to differentiate itself.

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, no prerequisites (e.g., the company must already have been enriched), and no exclusions stated. The agent must infer the scenario entirely.

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

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

No annotations are provided, so the description carries the full burden. It reveals nothing about read-only semantics, authentication needs, result limits, pagination, or how the three criteria combine (AND vs OR / ranking). The mention of an 'indexed' search is the only behavioral hint.

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

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

A single tight sentence with the resource and search fields front-loaded and no filler. Brevity comes at the cost of omitted guidance, but the sentence itself is well formed.

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 an output schema present, return values needn't be described, but for a three-parameter search with no annotations and zero schema coverage the definition omits how criteria combine, result limits, ordering, and empty-result behavior. Too thin for the tool's flexibility.

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 schema documents none of the three parameters. The description partially compensates by mapping concepts to parameters (name→query, UF→uf, CNAE prefix→cnae), but gives no formats, examples, or explanation of partial/prefix matching behavior.

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

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

States a specific verb (search) and resource (companies) and names the searchable dimensions (name, UF, CNAE prefix), so the agent knows exactly what this does. It does not, however, distinguish itself from sibling list_companies or get_company_details, which could plausibly retrieve similar data.

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

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

No guidance on when to prefer this over list_companies, get_company_details, or enrich_company_ai. The word 'indexed' hints at a search-index-backed lookup but no conditions, prerequisites, or exclusions are stated.

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