massa

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

Annotations only declare readOnlyHint/openWorldHint; the description adds the real behavioral payload: the 100-row hard stop and what the response contains when it trips, the xlsx download-link special case with a handling instruction, seed determinism guarantees, and the field-by-field error shape for invalid schemas. This is information no annotation or schema conveys.

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?

Purpose is front-loaded and every sentence carries a distinct rule (row cap, fallback, xlsx link, seed, errors) with no filler. The single dense paragraph is somewhat heavy, but nothing is redundant.

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

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

For a 4-parameter tool with nested schema and an output schema present, the description covers everything an agent needs to call it correctly: size limits, format-specific return behavior, seed semantics, and error handling. Return-value detail is legitimately delegated to the output schema.

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%, so the baseline is 3, but the description adds meaning beyond the schema: it explains why seed matters (identical output with the same seed and schema; a random one is drawn and returned when absent) and ties the row ceiling to the rows parameter. It adds real semantic value without documenting every field.

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?

Opens with a specific verb and resource ('Gera massa de teste a partir de um schema JSON do massa') and immediately states the output forms (csv, json, sql, xlsx link). An agent can distinguish this from importar_ddl or validar_documento without opening any schema.

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

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

Gives concrete operating conditions: up to 100 rows per call, nothing is generated above that and the response falls back to the /api/generate curl path, and xlsx bypasses the row ceiling. It does not name sibling tools (listar_tipos only appears inside the schema), so it stops just short of explicit alternative routing.

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

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

Annotations declare readOnlyHint=true, openWorldHint=false and idempotentHint=false; the description goes beyond them by explaining the randomness/seed contract ('omitida, o servidor sorteia uma e a devolve') and the error semantics for type-inapplicable options. That is real behavioral context, though it does not discuss volume/rate considerations or what a partial failure across 'quantidade' documents looks like.

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 tight sentences, front-loaded with the action and count range, then the type list, then the constraint/error rule and the seed return. Every sentence carries new information and nothing is 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?

With an output schema present, return values need not be enumerated, and the description still adds the non-obvious seed-return fact. For a 15-parameter tool with full schema coverage and clear annotations, the type/option interaction and error behavior are the only real gaps an agent would face, and both are covered.

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

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

Schema coverage is already 100%, so the baseline is 3. The description adds value by summarizing the cross-parameter constraint matrix (uf only for cpf, alfanumerico only for cnpj, bandeira only for cartao, banco only for conta, size/character rules only for senha) and by declaring that a mismatched option is an error rather than being ignored.

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 precise verb+resource+scope: generates 1 to 100 valid documents of one of five enumerated types (cpf, cnpj, cartao, conta, senha), and adds a differentiating guarantee that check digits are computed rather than fabricated. It never names a sibling, so an agent gets no help distinguishing it from the 'gerar' or 'validar_documento' tools from the text alone.

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 guidance is implied through the per-type option matrix ('cada tipo aceita só as suas opções') and the explicit error rule for mismatched options, which tells an agent how to combine parameters. However, there is no statement of when to choose this tool over the sibling 'gerar' or 'validar_documento', and no prerequisites are described.

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, openWorldHint=false and idempotentHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: type inference is heuristic (from the column name, CHECK constraint, or SQL type) and it emits warnings for columns needing review, which tells the agent results may be imperfect and need validation.

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 dense sentences that lead with the conversion and end with the next-step instruction; every sentence carries information. It is slightly packed with inference detail mid-sentence, but nothing is wasted or redundant.

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

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

An output schema exists, so return values need not be spelled out, and the description still gives the useful shape (schema, table name, dialect, warnings). Together with the annotations and full parameter coverage, an agent has enough to invoke it correctly, with only minor gaps around limits (e.g. only-first-table handling is in the schema, not the 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?

There is a single parameter with 100% schema description coverage, so the schema already documents it, including 'a primeira tabela é importada'. The description's only added value is implying the dialect is auto-detected rather than supplied as a parameter, which is marginal over the structured 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?

States a precise verb+resource (imports/converts a CREATE TABLE into a 'massa' schema) and enumerates the supported dialects (Postgres, MySQL, Oracle, SQL Server). It also explains how column types are derived, which separates it from the sibling generation tools that consume the resulting schema.

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 a clear workflow condition: pass the resulting schema to 'gerar' (with table and dialect) to obtain INSERTs, implying this tool is the first step and 'gerar' the second. It lacks an explicit when-not or a statement about what to do with an already-validated schema, so it stops 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully adds what the payload contains (groups, descriptions, per-type parameters, JSON schema format), but it adds no cost/auth/rate-limit context and an output schema already documents the return shape.

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?

One compact sentence that front-loads the resource and the enumeration, followed by a short imperative. Slightly dense but nothing is wasted and the call-to-action is last, which is appropriate.

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, read-only discovery tool with an output schema and clear annotations, the description says enough: what it returns and when to call it. No open questions remain that would block a correct 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?

The tool takes zero parameters, so per the rubric the baseline is 4. The description correctly implies no input filtering is required beyond the call itself.

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 (tipos de campo) and even enumerates concrete examples (nome, cpf, cnpj, cartao_credito...), plus what each entry contains (grupo, descrição, parâmetros). It does not explicitly contrast with the generation/validation siblings, but the discovery role is unmistakable.

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?

"Chame antes de montar um schema" gives an explicit precondition for calling the tool, which is exactly the sequencing an agent needs. It stops short of naming alternatives or when not to call it, so it lands at 4 rather than 5.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=false and idempotentHint=false. Beyond those, the description adds that input may carry or omit masks and that nothing is generated, which is genuinely useful side-effect context for a validator.

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?

Front-loaded purpose sentence followed by two short supporting sentences; the long type enumeration is dense but necessary to convey coverage. No filler sentences, though the enumeration makes the single sentence heavy.

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 no explanation, and annotations cover the safety profile. The description supplies the type list, conditional parameter dependencies and mask tolerance, leaving only minor gaps such as format expectations for banco codes.

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 all four parameters (tipo, valor, banco, agencia) are already documented in the schema, including the conditional requirements. The description only restates the banco/agência dependencies and adds the cartao return detail, so baseline 3 applies.

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

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

States a specific verb ('Confere se um número é válido') and resource, enumerates every supported document type, and clarifies scope with 'pela regra oficial'. The closing 'Não gera nada' cleanly separates it from the sibling gerar_documento.

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

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

Gives per-type conditions for use ('agencia precisa do banco', 'conta precisa do banco e da agência') and implicitly rules out generation via 'Não gera nada'. It never names an alternative tool explicitly nor states when validation is inappropriate, so it stops short of full when/when-not guidance.

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