Tribunal TRT24: Certidão Eletrônica de Ações Trabalhistas (CEAT)

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

The description discloses behavioral details beyond the annotations: it explains that using a config header yields a 'permanent, non-expiring connection' while pasting a token gives a 'session-only login'. It also clarifies the outcome of calling with no arguments (getting the link). These details align with the idempotentHint and non-destructive annotations, and no contradictions are present.

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

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

The description is three sentences long and efficiently conveys the essential information. It is front-loaded with the purpose, then details usage options. While slightly dense, it avoids unnecessary verbosity and each 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 single-parameter tool with no output schema, the description covers all necessary aspects: purpose, usage, token semantics, and behavioral outcomes. It is complete enough for an agent to successfully invoke the tool in both direct-token and config-based scenarios.

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

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

With 0% schema description coverage, the description fully compensates. It explains that the 'token' parameter is a JWT to paste for a session-only login, and that omitting it returns the login link. This provides semantics the schema lacks entirely, making the parameter's purpose and usage clear.

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

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

The description clearly states the tool's purpose: to authenticate the MCP server for IDE agents by logging in and obtaining an access token. It explicitly mentions the resource (MCP.AI server) and action (authenticate), and it distinguishes itself from sibling tools by focusing on authentication rather than connection or other utilities.

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 explicit usage instructions: how to permanently add the token to the server config, or how to use a session-only token via the token parameter, and how to get the link by calling with no args. It gives clear context on when to use each approach, but it does not explicitly compare with sibling tools like 'connect' 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value by explaining what the response looks like in different states (all connected vs. missing credentials), and clarifies the connect_url behavior for the toolkit and per-install URLs. This goes beyond what annotations convey. However, it doesn't specify the exact format of the response or possible error/exception behaviors.

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 sentences, highly informative. The first sentence states the core purpose; the second explains the two key behavioral states. No wasted words, no redundancy with annotations or 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 read-only status tool, the description covers the main behavioral aspects: what it returns when connected (authenticated:true, empty pending[]) and what it returns when credentials are missing (connect_url for toolkit and per-install URLs). Slight deduction for not explicitly describing the authenticated:false case outcome in terms of URL structure or alternative states. Overall, well-suited to its simple complexity.

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 0 parameters and the schema coverage is 100% (vacuous). Per the rubric, 0 params = baseline 4. The description doesn't need to add parameter information since there are none. It uses the available textual space to describe behavior instead.

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 this tool returns connection status and URLs, which is a specific verb+resource combination. It distinguishes itself from siblings by being the status check tool (vs. authenticate, marketplace, etc.). It could theoretically be more explicit about the tool name 'connect' mapping to checking connectivity, but the behavioral description is clear.

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

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

The description implies when to use this tool: to check connection status and get URLs, with explicit behavior for connected vs. missing credentials states. It doesn't explicitly name an alternative for when not to use it, but the contrast with siblings like 'authenticate' and 'marketplace' is implicit. Slight deduction for not explicitly saying 'use this when you need to verify connectivity' as a usage directive.

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

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

The description discloses crucial behavioral traits beyond the annotations: it states that writes require workspace owner/admin, explains that invoke works even when the MCP isn't installed, and details the connect/checkout link flow for authentication and payment. It also clarifies that install makes permanent changes. These details go well beyond the basic annotations (readOnlyHint: false, openWorldHint: true) and are consistent with them.

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 long, dense single block of text. It front-loads the purpose and core flow but packs extensive detail (permissions, link flows, prompt library) without clear sectioning. While every sentence carries information, the lack of formatting hurts scannability, and some repetition exists (e.g., restating 'mcp.ai' multiple times). It earns a middling score for density over 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?

Given the tool's complexity and lack of an output schema, the description covers the key aspects: the core flow, the distinction between invoke and install, permission requirements, payment/authentication behaviors, and the prompt library. It explains what list_tools returns and what describe provides. It is fairly complete for a high-level overview, though some niche actions (resume, report_context) are not elaborated.

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

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

With 0% schema description coverage, the description must compensate for parameter meanings. It does explain the high-level flow and maps some parameters (action, mcp_id, tool_id, arguments) to their roles in the search-describe-invoke pipeline. It also covers prompt library parameters like prompt_slug and prompt_body. However, many parameters (immediate, tier_slug, conversation, prompt_targets, cancel_reason, etc.) remain undocumented, leaving gaps for a 23-parameter tool.

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

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

The description clearly states the tool's purpose: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It distinguishes itself from siblings by positioning itself as the central marketplace for discovering, describing, and invoking MCPs, while also covering the prompt library. This is a specific verb+resource with clear scope.

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

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

The description provides explicit guidance on when to use the core actions: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT in the active toolkit.' It also explains the search-describe-invoke flow and mentions alternatives like list_tools. However, it does not explicitly address when to use this tool versus sibling tools like the standalone report_bug, leaving some potential ambiguity.

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 provide idempotentHint=true, readOnlyHint=false, and destructiveHint=false, which already signal the safety profile. The description adds a behavioral detail about including the conversation array for reproduction, which goes beyond annotations. However, it does not disclose what happens after submission (e.g., ticketing, response) or any auth requirements, leaving some gaps.

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

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

The description is extremely concise—two sentences total—and immediately states the purpose. Every word earns its place; there is no filler or redundant phrasing. The key instruction about the conversation array is included efficiently.

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

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

The tool is relatively simple with 3 parameters and no output schema. The description covers the core purpose and one parameter's usage, but fails to explain the required 'message' parameter's expected content and the optional 'context' parameter. For an agent to invoke correctly, it needs more clarity on these, so the description is not fully complete.

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

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

Schema description coverage is 0%, so the description must compensate. It only addresses the 'conversation' parameter explicitly, leaving 'message' (required) and 'context' unexplained. The agent cannot infer what to put in 'message' or how 'context' is used, making the parameter semantics insufficiently clarified.

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

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

The description clearly states the tool's purpose: 'Report a bug, missing feature, or send feedback.' This is a specific verb+resource pairing that distinguishes it from sibling tools like authenticate, connect, or marketplace, which serve entirely different functions.

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

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

The description implicitly defines when to use the tool (for reporting issues) and provides a usage hint: 'Include the conversation array with recent messages for reproduction.' However, it does not explicitly state when not to use it or mention alternatives, but given that siblings are unrelated, the context is sufficiently 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and the description does not contradict these. The description adds minimal context by specifying that it shows 'current... versions' and stays consistent with the safety profile, but doesn't go beyond what one would expect from the annotations.

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

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

A single, eight-word sentence conveys the complete purpose with zero filler. Impossible to be more concise for a version-querying 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?

Given the tool's simplicity (0 params, no output schema, strong annotations covering safety), the description is largely complete for what it needs to convey. Slight deduction for not noting the purpose of exposing version info (e.g., troubleshooting) or any related tools.

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 0 parameters, so the baseline is 4 per the rubric. The description appropriately doesn't fabricate additional parameter details where none exist, and the schema is complete as an empty object.

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 'Show the current MCP platform and adapter versions' clearly states a specific verb and resource, and clearly conveys what the tool does. However, it doesn't explicitly distinguish itself from sibling tools, though none of the siblings (authenticate, connect, marketplace, etc.) overlap in purpose.

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

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

No guidance is provided on when to use this tool vs alternatives. For a version-checking tool, one might expect at least an implicit note about it being for diagnostic/troubleshooting purposes, but there's no such context.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description only needs to add context about what is returned. It does so by enumerating the components (installed MCPs, connection status, accounts, and tool counts), which exceeds the baseline for annotation-supported transparency. No contradictions or hidden behaviors are unaddressed.

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, well-structured sentence that front-loads the primary action (returns) and then lists the specific data points. Every word adds value, with no filler or repetition.

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

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

With no output schema, the description must convey what the tool returns. It does so by specifying the exact components (installed MCPs, connection status, accounts, and tool counts). While it does not describe the format (e.g., JSON structure), the given information is sufficient for an agent to understand the tool's output type. It is a simple info tool, and the description is complete for its purpose.

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. The description correctly does not attempt to explain parameters, and the schema already confirms no inputs. No additional semantic information is needed or provided.

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 it returns the current toolkit state, listing installed MCPs, connection status, accounts, and catalog tool counts. This is a specific verb+resource (returns + toolkit state) and implicitly differentiates from siblings like connect or authenticate, which are action-oriented. However, it does not explicitly name an alternative or scope restriction, so it misses the top tier.

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

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

The description implies the tool is for inspecting current state but gives no explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives. Sibling names suggest the tool is the go-to for status, but the absence of direct guidance keeps it at a minimal viable level.

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

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

As annotations já indicam readOnly, idempotent e não destrutivo, e a descrição adiciona contexto relevante além delas: exigência de pagamento pré-pago, ausência de credenciais da plataforma, acesso a informação não sigilosa de fonte oficial e papel de controlador do cliente sob a LGPD. Faltam detalhes sobre resposta ou limites, mas o contexto é útil.

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?

Texto é compacto e informativo: começa com a finalidade, depois adiciona os pontos operacionais e jurídicos. Não há repetição relevante, e cada frase agrega um aspecto distinto da ferramenta.

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

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

A ferramenta tem três parâmetros, schema sem descrição e sem output schema, e o texto não explica o formato esperado da chamada nem o retorno da consulta. A descrição é suficiente para entender a finalidade, mas incompleta para um agente invocar corretamente sem suposições adicionais.

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 semântica do schema é de 0% e a descrição não explica nenhum dos três parâmetros: cpf, cnpj e cpf_solicitante. Não há orientação sobre qual preencher, quando usar CPF versus CNPJ, nem por que cpf_solicitante é obrigatório. A descrição não compensa a falta de documentação nos parâmetros.

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 identifica o recurso com precisão: consulta à CEAT (Certidão Eletrônica de Ações Trabalhistas) no âmbito do Tribunal TRT24, em fonte oficial. O verbo de ação ('consulta') está presente e o escopo é específico o suficiente para diferenciar a ferramenta dos demais tools, que são de autenticação, marketplace, suporte e informação.

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

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

A descrição dá contexto de uso relevante: consulta oficial brasileira, mesma informação disponível ao cidadão, sem credenciais da plataforma, cobrança por consulta com crédito pré-pago e responsabilidade LGPD do cliente. Não há alternativas explícitas, mas o contexto de uso e as condições práticas são suficientemente claros.

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