mcp-juridico-brasil

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

With no annotations, the description carries the disclosure burden. It does reveal a non-obvious behavioral trait: the tool rejects aggregators, isolated LexML, and jurisprudence without official full text. It does not disclose whether the operation is read-only, whether it mutates anything, or what happens with accepted citations.

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 sentence with no filler, and the key restriction is front-loaded. It is appropriately short for a one-parameter tool, though the brevity borders on cryptic.

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 documentation is not required, and the tool is structurally simple. Even so, the description omits the main action and input structure, leaving too much to inference. The refusal criteria alone are not a complete operating context.

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

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

Schema description coverage is 0%, so the description must compensate. It gives domain-level clues about citation source types but does not define any field of the 'citacoes' array objects. This is insufficient for an agent to construct a valid input confidently.

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 rejection behavior ('Recusa...') for three citation categories, which adds operational detail beyond the tool name. However, it never explicitly says the core action 'audit' or 'validate', so the reader must infer the main purpose from the tool name. It also does not differentiate itself from 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?

No guidance is provided on when to choose this tool over alternatives; it does not name any sibling or condition. The refusal rule implies a validation context but leaves the selection decision entirely to the agent.

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 behavioral burden. It adds meaningful context by revealing the tool consults the public DataJud API, covers 91 tribunals, and becomes slower when no tribunal is specified. It does not disclose potential failure modes, rate limits, or authentication expectations, but for a read-style public API lookup the disclosed context is reasonably helpful.

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 and front-loaded. The first sentence states the purpose, the second describes the data source and return contents, and the third gives relevant scope coverage. Every sentence contributes useful information with no filler.

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 an output schema exists and the input schema fully documents both parameters, the description is largely complete for direct invocation. It covers data source, scope, and return categories, though it does not provide explicit sibling-routing guidance or failure/error expectations.

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 schema already documents both parameters. The description reinforces the CNJ-number concept but adds no parameter-level meaning beyond what the schema provides, such as format requirements or the performance implication of omitting tribunal.

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 and resource: 'Busca os dados de um processo judicial pelo número CNJ' and enumerates the returned data (metadados, classe, assuntos, órgão julgador, partes, movimentações). It is clear, but it does not explicitly differentiate this tool from closely related siblings such as listar_movimentacoes, which may also expose movement 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?

The description implies the tool is used to look up process data by CNJ number and provides useful operational guidance about the slower search when tribunal is omitted. However, it never states when to prefer this tool over alternatives like listar_movimentacoes or resumir_andamento, nor does it mention exclusions or complementary use.

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 present, the description carries the full behavioral burden. It discloses the key calculation behavior: business days, next-day start term, and judicial recess suspension from 20 Dec to 20 Jan. It does not describe fallback behavior or errors, but the core behavior is explicit and non-destructive.

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

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

Two short sentences with the core purpose front-loaded and the legal details compactly presented. Every phrase contributes value and there is no filler.

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 complete for a calculation tool: it states the legal rules, the calendar scope, and the calculation behavior. The input schema thoroughly documents all parameters, and an output schema exists, so return values do not need to be explained in 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?

Schema description coverage is 100%, so the baseline is 3. The description adds legal context but does not provide parameter-level semantics beyond what the schema already documents for uf, tipo_ato, tribunal, and data_intimacao_iso.

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 names a specific verb and object: 'Calcula o próximo prazo processual em dias úteis com calendário forense.' It also cites the exact CPC articles implemented, clearly distinguishing it from sibling tools such as buscar_processo_por_numero and listar_movimentacoes.

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 intended use obvious: calculate a procedural deadline using business days and forensic-calendar rules. It does not explicitly list exclusions or alternative tools, but none of the sibling tools appear to offer the same deadline-calculation function.

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?

This is an excellent behavioral disclosure. The description explicitly warns that the action is irreversible, registers an official timestamp, starts a legal deadline, defaults to dry-run, and depends on an environment variable. This goes far beyond the annotations' destructiveHint and idempotentHint, giving the agent complete awareness of side effects.

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?

Although long, the description is highly structured and every section earns its place. The high-risk warning is front-loaded, the safety gate is clearly separated from credentials, and the text is formatted for quick scanning. This is appropriate for a high-stakes, irreversible operation.

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 prerequisites, side effects, irreversibility, the dry-run fallback, required credentials, and operational constraints. Together with the output schema and annotations, it fully equips an agent to decide whether and how to invoke the tool safely.

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

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

The input schema already covers all three parameters with 100% description coverage, so the baseline is 3. The description adds meaningful extra context by tying confirmar to the safety gate, clarifying id_intimacao's provenance via listar_intimacoes, and emphasizing the real-world legal effect of the parameters.

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

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

The description clearly states the action ('Confirma a leitura de uma intimação'), the target system ('Domicílio Judicial Eletrônico'), and the legal consequence (starting the procedural deadline). This makes the tool immediately distinguishable from siblings like listar_intimacoes or buscar_processo_por_numero.

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 strong contextual guidance: it requires confirmar=True and DJE_PERMITIR_CONFIRMACAO_LEITURA=true for real execution, and it mentions that id_intimacao comes from listar_intimacoes. It does not explicitly state when not to use the tool or compare it to alternatives, so it stops short of a 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the output structure and that local sources are involved; it does not explain side effects, read/write behavior, how sources are selected, or what the response contains.

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 with no filler, but it is so terse that it becomes cryptic. It conveys the structural chain, yet omits enough detail that the brevity is under-specification rather than polished conciseness.

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

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

This is a complex six-parameter legal tool with no annotations and no schema-level descriptions. The one-line phrase is far from sufficient for an agent to know when, why, or how to call it, even if an output schema exists.

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 six parameters with 0% description coverage, so the description must compensate. It only alludes to fatos, pedido, and perhaps lei/Norma through the structural chain, while tese, jurisdicao, and data_referencia remain unexplained and unmapped.

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 'Estrutura Fato→Prova→Norma→Subsunção→Consequência→Pedido com fontes locais' communicates that the tool works with legal arguments and uses a defined structural chain, so it is not a bare tautology. However, it lacks an explicit action verb and does not distinguish this tool from near-sibling redigir_argumento_juridico.

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 invoke this tool instead of alternatives. It never mentions conditions, prerequisites, or exclusions, and it does not reference related tools such as redigir_argumento_juridico or preparar_minuta_juridica.

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. It discloses that results are organized into four explainable perspectives, include a source, and have redundancy reduction, but it does not clarify ordering, filtering behavior, or whether the operation is read-only.

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 short sentence with no filler; the core search behavior and unique output features are front-loaded. It is concise, though the brevity sacrifices detail that other dimensions capture.

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 seven parameters, no annotations, and a high-risk ambiguity around search alternatives, the description is too thin to fully guide correct invocation. An output schema exists, which covers return shape, but parameter semantics and selection criteria still depend on external inference.

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 needed to compensate, but it does not explain pergunta, lei, limite, jurisdicao, tipo_fonte, diversidade, or data_referencia. The phrase 'redução de redundância' hints at the diversity parameter, but this is indirect and insufficient.

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 clear action ('Busca') and, combined with the tool name, identifies the resource as the legal corpus. It also specifies a distinctive behavior: retrieving four explainable perspectives with sources and redundancy reduction, which sets it apart from simple listing or synchronization 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?

There is no guidance about when to use this tool instead of related search tools such as pesquisar_lexml or construir_argumento_juridico. The description implies a search use case but does not state prerequisites, exclusions, or alternative 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?

With no annotations provided, the description carries the full disclosure burden. It reveals only that the tool produces an explanation of voting, disagreement, and repetition, but says nothing about whether it triggers external analysis, how it uses the `diversidade` threshold, or what workflow it executes. The disclosure is minimal and mostly restates the obvious diagnostic function.

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 single sentence is structurally clean and front-loaded with the main action. However, at roughly 11 words for a complex 7-parameter diagnostic tool with zero schema coverage, this brevity crosses into under-specification rather than genuine conciseness.

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?

High complexity (7 parameters, 1 required, 0% schema coverage, no annotations) combined with an 11-word description leaves the tool essentially unusable for correct invocation. The output schema mitigates return-value uncertainty, but the agent is left guessing what `pergunta` expects, what `diversidade` controls, and what the overall workflow is.

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 7 parameters. It offers only loose conceptual hints ('discordância' relates to `diversidade`; 'votaram' implies a question like `pergunta`), but never explains the roles of `lei`, `jurisdicao`, `tipo_fonte`, `limite`, or `data_referencia`. This is insufficient compensation for a 7-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 uses a specific verb and resource ('explica como as perspectivas votaram... discordância ou repetição') and is functionally distinct from all siblings. However, it relies on unexplained jargon ('perspectivas votaram') that neither the tool name ('neurodiversidade jurídica') nor the parameters clarify, making the core purpose fuzzy for an agent.

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 whatsoever about when to use this tool versus alternatives. It does not name any sibling, state conditions for selection, or mention any exclusion criteria. An agent must infer its place among 25 related legal tools with no support.

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 disclosure burden, and 'Mostra' clearly signals a read-only operation on a 'banco jurídico local,' implying no external calls or mutations. It also discloses what the output covers. It does not mention auth or performance, but for a zero-parameter local status tool the key behavioral traits are covered.

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 sentence with a front-loaded verb and concrete output categories; 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?

For a no-parameter informational tool with an output schema, the description covers the essential output dimensions and clearly signals it inspects the local corpus. It is slightly weaker on guiding the agent to choose it over sibling corpus tools, but that is a usage-guideline gap rather than a completeness gap for the call itself.

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 are no parameters, so the input schema is complete and there is nothing for the description to clarify. The description instead adds meaning about the output dimensions, 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 states a specific verb ('Mostra'), a resource ('banco jurídico local'), and the exact information returned (coverage, dates, hashes, location). This clearly separates it from siblings like listar_fontes_corpus_juridico and consultar_corpus_juridico, which cover different aspects of the corpus.

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

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

No guidance is provided about when to use this tool instead of the closely related corpus tools. The description does not mention alternatives, exclusions, or a recommended context such as checking corpus health before synchronization.

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 fully carries behavioral disclosure and does so well: it says the run is finite, fault-tolerant, deduplicated, failures do not cancel other processes, and—critically—it is read-only and never confirms notifications in DJe. This gives the agent a clear safety model.

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?

Five short sentences, each carrying distinct information: scope, required target fields, dedup, fault tolerance, and side-effect safety. The purpose is front-loaded and every sentence 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 no-annotation tool with a non-trivial RPA behavior, the description covers input requirements, failure semantics, and side-effect safety; the output schema handles return values. The only notable gap is the undocumented 'concorrencia' parameter, and the description does not say what happens when more than 50 targets are supplied.

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 documents the required shape of each 'alvos' entry (numero_processo, tribunal, desde_iso) and deduplication behavior, but it says nothing about the 'concorrencia' parameter, leaving its semantics to inference from its name and default 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 first sentence states a concrete action and scope: executes a finite, fault-tolerant RPA cycle for up to 50 processes. This clearly identifies the batch-monitoring function, but it does not name or contrast any sibling such as monitorar_processo, so differentiation is left to the reader.

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 signals batch context (até 50 processos) and implies this is for multiple targets, but it never states when to choose this tool over singular tools like monitorar_processo or listar_movimentacoes. There are no explicit when/not-when conditions or 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?

Não há annotations, então a descrição carrega o peso da transparência. Ela revela traços úteis: o HTML é autocontido e o resultado deve passar por revisão humana. Contudo, não informa efeitos colaterais, permissões necessárias, limitações ou se grava arquivos no sistema.

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 palavras redundantes, carregando a informação principal no início. É concisa, embora pequena demais para cobrir a complexidade do 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?

Com 8 parâmetros, 0% de cobertura de descrição no schema e nenhuma annotation, a descrição é insuficiente para um agente invocar a tool corretamente. A existência de output schema ajuda nos retornos, mas o agente ainda não sabe como preencher os parâmetros nem quando escolher esta tool.

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% e a descrição não define nenhum dos 8 parâmetros. O significado de tese, fatos, pedido, lei, jurisdicao, nome_arquivo e data_referencia fica totalmente a cargo dos nomes, sem orientação sobre formatos, obrigatoriedade ou relações entre eles.

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 é específica: verbo 'Gera' + recursos 'HTML Visual Law autocontido' e 'auditoria JSON'. Diferencia-se claramente de irmãos como gerar_documento_word_juridico, porque declara o formato Visual Law HTML.

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?

O uso é inferido pela geração de Visual Law, e a frase 'sempre sujeito a revisão humana' orienta que a saída precisa ser checada. Porém, não há indicação explícita de quando usar em vez de alternativas como gerar_documento_word_juridico ou redigir_argumento_juridico.

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. It mentions clickable sources and visible gates, but does not explain side effects, file creation behavior, overwrite risks, required permissions, or how the harness state is consumed. This leaves significant behavioral ambiguity.

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 with no filler words, which is efficient and easily parsed. The brevity is a strength, though the cryptic terms 'harness' and 'gates' reduce clarity and force the agent to infer their 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?

This is a document generation tool with eight parameters and no annotations, so a richer description is needed. The output schema may cover return values, but the description still omits important contextual details: what 'harness' refers to, how 'fatos' should be structured, how the output file is named, and whether existing files are replaced.

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 does not explain any of the eight parameters. Required fields like 'titulo', 'tese', 'fatos', and 'pedido' are only understandable from their names, and optional parameters such as 'lei', 'jurisdicao', 'nome_arquivo', and 'data_referencia' receive no additional 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 uses a clear verb ('Gera') and identifies the resource ('DOCX formal'), which conveys the tool's core purpose. However, terms like 'harness', 'fontes clicáveis', and 'gates visíveis' are domain jargon that may confuse an agent, and the description does not differentiate this tool from related siblings such as 'gerar_documento_visual_law'.

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 choose this tool over alternatives like 'gerar_documento_visual_law', 'preparar_minuta_juridica', or 'redigir_argumento_juridico'. No prerequisites, exclusions, or scenario-based guidance are provided.

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 are absent, so the description carries the behavioral burden. 'Lista' strongly implies a read-only operation, and the phrase 'aceitas pelo RPA local' clarifies that it enumerates pre-accepted sources rather than fetching live data. It does not explicitly state that no mutation or sync occurs, but for a zero-parameter listing tool this is a minor gap rather than a serious 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 entire description is one focused sentence with no filler, and the key verb and resource appear immediately. It is appropriately sized for a tool with zero parameters and an output schema.

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 listing tool with an output schema, the description covers the essential facts: what items are returned and the acceptance context. A minor gap is that 'RPA local' is not defined, but sibling context and the output schema fill most potential needs, so it is nearly 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 tool has no parameters, so the baseline is 4 and there is nothing for the description to add beyond the schema. The sentence still enriches the meaning by naming exactly what is listed (main laws and official URLs), even though no parameter semantics are needed.

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 a concrete resource ('leis principais e URLs oficiais aceitas pelo RPA local'), making the tool's purpose immediately obvious. It also distinguishes this listing tool from corpus siblings like consultar_corpus_juridico and sincronizar_corpus_juridico by scoping it to accepted sources. No ambiguity remains about what is returned.

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 described behavior implies the tool should be used when the agent needs to enumerate the main laws and official URLs accepted by the local RPA. However, it gives no explicit when-not-to-use guidance or pointers to alternatives such as sincronizar_corpus_juridico or consultar_corpus_juridico. With no parameters, the use case is reasonably inferable, but it is not made explicit.

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

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

With no annotations provided, the description carries the behavioral disclosure burden. It explicitly states 'Operação SOMENTE LEITURA - sem efeito jurídico', discloses that secret-justice intimações have suppressed content, and lists required credentials. It does not cover pagination or error handling, but the disclosed traits are meaningful and not redundant.

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 front-loaded with the main purpose and read-only safety notice, followed by return behavior and a compact bulleted credential list. There is no redundant or filler text, and each sentence contributes essential information.

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

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

The description is complete for an agent to invoke the tool correctly: it explains the operation's read-only nature, the credential requirements, the filtering context, and the secret-justice special case. Since an output schema exists and the input schema is fully documented, nothing critical is 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?

Schema description coverage is 100%, so all three parameters (limite, numero_processo, apenas_pendentes) are already documented with defaults and examples. The description does not add parameter-level semantics beyond the schema, though it adds useful environment-variable context for authentication. 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 states a specific verb and resource: 'Lista comunicações processuais do Domicílio Judicial Eletrônico (DJe)', and clarifies the scope by enumerating intimações, citações e notificações. The focus on DJe communications and the read-only qualifier make it distinguishable from siblings like listar_movimentacoes and confirmar_leitura_intimacao.

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 clearly conveys that this is the read-only listing operation for DJe communications and specifies the required credential environment variables. It does not explicitly state when to prefer an alternative or when not to use this tool, so it falls short of a 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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It does disclose the output fields, ordering, and the performance rationale for the required tribunal parameter. However, it does not mention failure modes, pagination beyond the limit parameter, or any other side effects, though none seem likely for a read-only listing tool.

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

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

The description is two short sentences, front-loaded with the main purpose and followed by a concise statement of the return format and ordering. There is no fluff, and every sentence 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 listing tool with three parameters, complete schema coverage, and an output schema, the description is largely sufficient. It explains what is returned and the ordering. The only gap is the lack of explicit behavior around errors or edge cases, but these are less critical given the low complexity and read-only nature of the tool.

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 each parameter is already documented in the input schema. The tool description adds context about what is returned but does not add additional meaning to the parameters themselves. A baseline of 3 is appropriate when the schema already provides complete parameter 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 states a clear verb ('Lista') and a specific resource ('movimentações de um processo judicial'), and goes on to specify the returned fields and ordering. It does not explicitly differentiate from siblings like listar_intimacoes or resumir_andamento, but the resource is unambiguous enough that an agent can tell what the tool does.

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

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

The intended use is implied by the description: list recent movements for a judicial process. However, there is no explicit guidance on when to choose this tool over alternatives such as resumir_andamento or listar_intimacoes, nor any mention of exclusions or prerequisites. The tribunal parameter note adds a performance constraint but not usage 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?

No annotations are provided, so the description carries the transparency burden. It discloses the source (official MTE catalog) and that both active and revoked NRs are listed, but does not mention network dependency, freshness, failure behavior, ordering, or output format. This is adequate for a simple listing tool 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?

A single sentence front-loads the action and result with no filler, no repetition of the tool name, 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 parameterless listing tool with an output schema, the description is nearly complete: it identifies the source and scope. It does not mention error or unavailability behavior, but the low complexity and presence of an output schema reduce the need for more detail.

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 the zero-parameter baseline of 4 applies. The description does not need to add parameter-level 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 uses specific verbs ('vasculha' and 'lista'), names the resource ('catálogo oficial do MTE'), and explicitly states the result set includes both vigentes and revogadas NRs. This clearly differentiates it from the sibling synchronization tool.

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

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

The description implies the tool is used when someone needs a list of NRs from the official MTE catalog, but it does not explicitly state when to use it over alternatives or provide any exclusions. The related sibling 'sincronizar_normas_regulamentadoras' is not referenced.

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 behavioral burden. It discloses the in-memory, session-scoped nature and exactly what the tool returns (numbers list and total), making it evident that this is a read-only listing operation.

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

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

The description is compact and informative, with the key scoping information front-loaded. However, the first two sentences largely restate the same idea ('Lista processos com snapshot' vs 'Retorna os números... snapshot salvo'), introducing minor 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?

For a zero-parameter listing tool with an output schema, the description is fully sufficient. It explains what the tool does, what it returns, and how to obtain full snapshot data, leaving no critical gap for 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 input schema has 0 parameters, so the baseline is 4. The description adds no parameter syntax, but none is needed; it still clarifies the output shape the agent should expect.

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 resource ('processos com snapshot em memória na sessão atual'). It clearly distinguishes itself from siblings like monitorar_processo by narrowing the scope to session-scoped saved snapshots and pointing to the processo://resource for full 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?

The description clearly defines its context: a session-limited listing of snapshots. The instruction to use the processo://{numero}/snapshot resource for full data provides a useful boundary, though it does not explicitly name alternative tools or state when not to use this tool.

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 correctly signals a read-only lookup via 'Lista' and identifies the content returned. It does not discuss data source, freshness, authentication, or rate limits, but for a zero-parameter catalog action those omissions are minor.

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 concise sentence with the action front-loaded and no filler. Every phrase ('suportadas', 'campos recomendados') conveys 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 parameterless listing tool with an output schema, the description is essentially complete. The only gap is the absence of an explicit bridge to sibling tools such as preparar_minuta_juridica, which would clarify the larger workflow.

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

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

The input schema has zero parameters, so the 0-param baseline of 4 applies. There is nothing additional the description needs to add about parameter 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?

The description uses a specific verb ('Lista') and a precise resource ('minutas suportadas') and adds what the listing contains ('os campos recomendados para cada uma'). It clearly separates this catalog/lookup tool from action-oriented siblings like preparar_minuta_juridica.

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 call this tool or when to prefer one of its siblings. It says only what it lists; it does not state that it should be consulted before preparar_minuta_juridica or mention any exclusions.

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

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

There are no annotations, so the description carries the behavioral disclosure burden. 'Lista' implies a read-only operation, and the description explicitly states it returns siglas usable downstream, clarifying the main behavioral and output contract. It does not mention pagination, ordering, or side effects, but for a simple zero-parameter enumeration tool this is sufficient.

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 short sentences with no redundant content. It front-loads the core purpose (listing supported tribunals) and then explains the practical value of the return values. Every sentence 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 list operation with an output schema available, the description fully covers what the tool does and why it matters. It states the total count, the output content (siglas), and the relationship to other tools' parameters. Nothing essential is 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 tool has zero parameters, so the baseline is 4. There is no parameter description needed, and the description adds relevant context by explaining that the returned siglas feed into the 'tribunal' parameter of other tools, which is more useful than simply noting there are no 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?

The description uses a specific verb ('Lista') with a clear resource ('todos os tribunais suportados pelo MCP') and adds a precise scope detail (91 total). It also states what the tool returns and how that output is used, making it clearly distinct from the many other 'listar_*' sibling 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 clearly indicates the tool's purpose: to provide valid court acronyms for the 'tribunal' parameter of other tools. This implies when an agent needs to know supported tribunals before calling other tools, this is the one to use. It does not explicitly state when not to use it or mention alternatives, but no competitors exist among the siblings.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It usefully states that this is a polling implementation with no real-time guarantee and that a push notification phase is planned. However, it does not cover failure modes, rate limits, or an explicit read-only guarantee.

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 main behavior and followed by a concise implementation note. Every sentence earns its place and there is no redundant information.

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

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

For a simple check-oriented tool with fully documented parameters and an output schema, the description is mostly complete. It could be stronger on when to use alternatives and edge-case behavior, but the core invocation context, including the polling/no-real-time caveat, is 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 description coverage is 100%, so the input schema already documents all three parameters, including ISO format and CNJ format requirements. The description adds little beyond the phrase 'após a data informada', but the schema does the heavy lifting, so the baseline score of 3 is appropriate.

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

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

The description clearly states the action and resource: it checks whether a process had an update after a given date. This is specific enough to understand the core function, but it does not explicitly differentiate from siblings such as executar_monitoramento_em_lote or listar_movimentacoes.

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: call this tool to determine whether a process was updated after a date. The mention of polling via DataJud without real-time capability is useful context, but the description does not explicitly say when to prefer alternatives like executar_monitoramento_em_lote or listar_movimentacoes.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It explains the protocol (SRU/CQL) and the return payload (URN, ementa, assuntos, resolver link), which is useful. However, it does not disclose limitations such as pagination behavior, external service dependency, or whether the search is read-only and safe to invoke without side effects.

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 and well-structured: it opens with the core action and resource, then lists accepted fields, optional filters, and return values. Every sentence adds distinct value with no redundancy or filler.

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

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

For a tool with 9 parameters, no schema descriptions, and no annotations, the description is incomplete. It covers high-level functionality but misses required-parameter semantics, pagination controls, and any guidance on how fields/filters interact, so an agent lacks enough detail to invoke it correctly in all 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?

The schema has 0% description coverage, so the text must compensate for the 9 parameters. It adds meaning for `campo` by listing accepted values and for the optional filters (tipo_documento, localidade, autoridade, ano_inicio, ano_fim). However, it completely omits the required `termos` parameter and the pagination parameters `limite` and `pagina`, leaving the most essential input unexplained.

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 clear, specific action: searching legal metadata in the official LexML collection via SRU/CQL. It further differentiates the tool by specifying accepted search fields, optional filters, and return values, making its purpose distinct from siblings like resolver_urn_lexml or consultar_corpus_juridico.

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 for use: searching LexML metadata with configurable fields and filters. It does not explicitly name alternative tools or state when not to use this tool, but the stated scope is enough for an agent to infer the appropriate scenario.

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

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

With no annotations provided, the description carries the full burden. It usefully discloses that the result always requires human review, which is an important behavioral expectation. It does not, however, clarify side effects, permissions, or whether the tool only generates text without modifying external 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 compact and front-loaded: it states the main purpose first, then lists accepted inputs, and ends with the human-review caveat. Every sentence contributes useful information without 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?

The description is incomplete for a tool with no annotations and no schema-level descriptions. It explains which document types are accepted and that human review is required, but it does not explain what 'dados' should contain or how 'objetivo' should be phrased, leaving a critical input opaque despite the output schema being present.

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 adds meaningful value for tipo_documento by enumerating accepted values and the alias 'ct', but it leaves objetivo, dados, and tom essentially unexplained. Since these are core parameters, the semantic gap is significant.

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 prepares a legal minuta and professional prompt anchored in local articles, which is a specific verb plus resource. The list of accepted document types adds useful scope, though it does not explicitly differentiate from sibling drafting tools like redigir_argumento_juridico or gerar_documento_word_juridico.

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 an explicit list of accepted document types, which implies when the tool is appropriate, and notes that human review is always required. However, it does not state when not to use this tool or suggest an alternative sibling, so the usage guidance remains somewhat inferential.

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 describes an internal-looking pipeline of rule, proof, application, adversarial review, and review, but fails to state whether the operation mutates data, requires permissions, is long-running, or what the output contains.

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 single sentence is compact and front-loaded with a verb, but it devotes its space to unexplained jargon and omits the practical details an agent needs. This reads as under-specification rather than economical 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?

With 6 parameters, 3 required, no annotations, and a close sibling, this description is far too incomplete. The presence of an output schema helps with return-value expectations, but purpose, usage context, and parameter semantics remain undefined.

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 names none of the six parameters (tese, fatos, pedido, lei, jurisdicao, data_referencia). The legal parameter names may hint at meaning, but the description itself adds no semantic or format information beyond the 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 states a verb (Executa) and a resource ('harness de regra, prova, aplicação, contraditório e revisão'), so it is not a pure tautology. However, the 'harness' concept is opaque, it does not say what the tool produces, and it does not distinguish this tool from the sibling construir_argumento_juridico.

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 alternatives such as construir_argumento_juridico, preparar_minuta_juridica, or auditar_citacoes_juridicas. No prerequisites, exclusions, or context cues are provided.

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 explicitly states that the operation is deterministic, does not consult the network, and that opening the returned URL remains subject to portal availability and security verification. This is strong, pertinent behavioral 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 two sentences with no filler. The primary purpose is front-loaded, and the second sentence adds necessary behavioral caveats without 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?

For a one-parameter, deterministic tool with an output schema, the description covers the operation, network behavior, and the post-resolution caveat. The output schema handles return-value details, so no critical calling information is 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 schema has no description for the single parameter `urn`, and schema description coverage is 0%. The description adds the domain meaning that the URN must be a Brazilian LEX URN, but it does not specify expected format, examples, or normalization behavior, so it only partially compensates for the 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 states a specific action — validating a Brazilian LEX URN and returning its official resolver — which clearly identifies the tool's function. This distinguishes it from sibling tools like pesquisar_lexml, which suggests searching rather than resolving a URN.

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

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

The description implies usage when a Brazilian LEX URN needs validation and resolution, and the deterministic/no-network note helps set expectations. However, it does not explicitly state when to prefer this tool over alternatives such as pesquisar_lexml, nor does it mention exclusions or 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?

No annotations are provided, so the description carries the full burden. It clearly signals read-only behavior with verbs like 'Retorna', 'busca', and 'devolve', and usefully discloses that the output includes instructions and that the MCP does not perform semantic summarization. It does not discuss side effects, permissions, or rate limits, but the read-only nature is evident.

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 and front-loaded, with the core purpose in the first sentence and operational context plus the crucial MCP/model boundary in the following sentences. Every sentence earns its place; there is no filler.

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

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

Given the simple parameter set, full schema descriptions, and the presence of an output schema, the description is complete enough for correct invocation. It states the data source, what is returned, and explicitly clarifies that summary generation is the model's responsibility, preventing a common misconception.

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

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

The input schema already provides 100% parameter coverage, including CNJ format for numero_processo and the tribunal default behavior, so the baseline is 3. The description adds no parameter-specific meaning beyond what the schema already states.

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 operation: retrieving structured process data from DataJud for LLM-generated summaries. It distinguishes itself by stating that semantic summarization is intentionally left to the model, not the MCP, which separates it from raw-data-fetching or drafting siblings. However, it does not explicitly name sibling tools or exclusion criteria, so it falls just 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: the agent should use this tool when it needs to produce a natural-language case summary, since the description says the data is returned 'para geração de resumo pelo LLM'. Yet there is no explicit when-to-use/when-not-to-use guidance and no reference to alternatives like buscar_processo_por_numero for raw process data.

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 transparency burden. It discloses that this is a finite RPA, describes the full pipeline (download, separate, embed, save), and importantly reveals idempotency behavior via SHA-256 with no reindexing of unchanged documents. It does not cover rate limits or authorization, but core side effects are transparent.

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, front-loaded sentences with no repetition. Each sentence adds non-obvious value: purpose, parameter-driven scope, and idempotency.

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 do not need to be described. The main invocation paths and idempotency are covered, but the undocumented 'concorrencia' parameter, absence of any annotation, and lack of guidance about running alongside other operations leave clear 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%, so the description must compensate. It richly explains 'fontes', including default behavior and the expected code source, but completely omits 'concorrencia'. With only two parameters, leaving one entirely undocumented is a significant gap for an agent deciding whether to adjust it.

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 sequence and resource: 'baixa, separa, embeda e salva artigos de fontes oficiais'. It clearly distinguishes the sync/ingestion role from query siblings like consultar_corpus_juridico and estatisticas_corpus_juridico, and also names the related listar_fontes_corpus_juridico as the source of codes.

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?

Provides clear context: omitting 'fontes' syncs the entire main catalog, while providing codes from listar_fontes_corpus_juridico scopes the operation. It lacks explicit 'when not to use' guidance or differentiation from sincronizar_normas_regulamentadoras, but the main use cases are clear.

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. It discloses that the tool persists embeddings and uses SHA-256, and that it discovers and extracts PDF items. However, it does not state whether existing embeddings are updated or replaced, whether network/MTE access is required, or whether the operation is idempotent.

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

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

The description is a single, front-loaded sentence that conveys the full pipeline without filler or redundancy. Each phrase adds a distinct stage: discovery, extraction, and persistence with integrity hashing.

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 two-parameter ingest operation with no annotations, the description is too thin: it omits the meaning of nrs and concorrencia, any prerequisites or side effects, and when this sync should be run relative to sibling corpus tools. The existence of an output schema reduces the need to document return values, but operational context is still 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?

Schema description coverage is 0% and the description does not explain either parameter. While names like 'nrs' and 'concorrencia' hint at meaning, the agent gets no explicit guidance about accepted values, units, or how the parameters affect the extraction/persistence pipeline.

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 names a concrete pipeline: discovers current PDFs on MTE, extracts items, and persists embeddings with SHA-256. It clearly identifies the resource (regulatory norms from MTE) and differentiates from siblings like listar_normas_regulamentadoras and sincronizar_corpus_juridico by describing ingestion and persistence rather than listing.

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 statement of when to call this tool or when to prefer an alternative such as sincronizar_corpus_juridico or listar_normas_regulamentadoras. The only guidance is implied by the verb 'sincronizar' in the name and the pipeline description.

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