Tribunal TJSP: Certidão Cível de 1º Grau

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

Beyond the annotations, the description reveals that this tool triggers browser login, can return a link when called with no arguments, and supports both session-only and permanent token-based authentication. It also clarifies the token must be a JWT. No contradiction with the readOnlyHint or idempotentHint 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?

The description is dense but reasonably concise, with the purpose stated first and the two usage modes clearly separated. It could be slightly cleaner, but every sentence adds necessary 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 one-parameter auth tool with no output schema, the description covers the core flows: browser login, link retrieval, session token, and permanent config. It does not specify the exact response format or error behavior, but it is sufficient for an agent to invoke it correctly.

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

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

The schema only defines 'token' as an optional string, but the description explains it is a JWT, that omitting it returns the login link, and that including it enables session-only login. This fully compensates for the 0% schema description coverage.

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 as logging in to MCP.AI and obtaining an access token, with a browser-based flow. It is specific about the resource, but it does not differentiate itself from sibling tools such as 'connect' or otherwise state what makes this tool the right one.

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

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

It gives concrete usage guidance: no arguments returns the login link, passing a token performs session-only login, and adding the Authorization header to config creates a permanent connection. It does not explicitly contrast this tool with alternatives or state when not to use it.

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

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

Annotations already declare the tool as readOnly, idempotent, and non-destructive. The description adds valuable behavioral details by outlining the response structure for the two main states (authenticated:true with empty pending[] vs. connect_url and per-install URLs). It does not contradict annotations and provides context beyond the safety profile.

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 long, front-loads the core purpose, and then provides the necessary conditional details. Every sentence earns its place without redundancy or wasted words.

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 tool with no output schema, the description completely mitigates the lack of structured output information by detailing the two main return scenarios. It covers authenticated state and credential-missing state, making the tool's behavior fully understandable. The sibling context does not require additional elaboration.

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 there is nothing to describe beyond the schema. The baseline for 0 params is 4, and the description provides no unrelated parameter information. It correctly focuses on the output 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 the tool's function with a specific verb ('Returns') and resource ('connection status and URLs'). It distinguishes from siblings like 'authenticate' by focusing on status, not the act of connecting. The two return scenarios are explicitly described, making the purpose unambiguous.

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

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

The description provides clear context on when to use the tool by describing the two possible outcomes (all providers connected vs. credentials missing). However, it does not explicitly mention alternatives or exclusions, though the sibling names make it evident this is for status checking rather than initiating authentication.

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 set readOnlyHint=false and openWorldHint=true, and the description adds substantial context: invoke runs uninstalled tools one-off without adding to the toolkit, missing credentials yield a connect link, empty wallet yields a checkout/top-up link, and writes require owner/admin. This goes beyond the basic flags and fully discloses side effects and prerequisites. No contradiction with 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?

The description is dense and information-rich, with helpful markers like 'Core flow:' and 'KEY:', but it is a long, multi-topic paragraph. Some phrases are redundant, and bullet points or separate sections would improve scanability. The length is partially justified by the tool's 14 actions, but it is not concise.

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

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

For a tool with no output schema and high complexity, the description is remarkably complete. It covers the full workflow, auth/billing edge cases, permission requirements, the prompt library, and retry behavior after connect/checkout links. It does not detail the return format of every action, but given the breadth, it provides enough context for safe and effective use.

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 description explains key parameters through the action flows, such as action, mcp_id, tool_id, arguments, and the prompt_* fields, but with 23 parameters and zero schema descriptions, it leaves many parameters (limit, query, immediate, tier_slug, cancel_reason, report_context, request_details) only inferable by name. It adds value but does not fully compensate for the schema's lack of descriptions.

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 what the tool is: the official mcp.ai marketplace, covering catalog discovery and execution. It outlines the core search→describe→invoke flow and explicitly distinguishes key actions like invoke vs install, making its purpose unambiguous and differentiated 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?

The description gives direct guidance on when to use which action: 'prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT', 'list_tools lists what is callable right now', and notes that writes require owner/admin. It also clarifies what to do when the wallet is empty or credentials are missing, giving clear decision paths.

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 non-destructive and idempotent behavior, so the description doesn't need to repeat that. It adds the guidance to include conversation for reproduction, which is useful behavioral context. No contradiction with 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?

Two concise sentences, front-loaded with purpose, no redundant wording. Efficient and to the point.

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?

Covers the essential use case (reporting issues) and a key hint (conversation for reproduction). However, it omits details like what happens after reporting, whether context is optional, or if message must be a specific format. For a simple tool, adequate but with noticeable 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 has 0% description coverage, so the description must explain parameters. It explains the purpose of 'conversation' but does not describe 'context' or provide detail on 'message' beyond its name. Message is required but its format or content isn't clarified, and context is left 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?

Description clearly states the verb 'Report' and the resources (bug, missing feature, feedback). It distinguishes from sibling tools (authenticate, connect, etc.) which are unrelated, making the purpose unambiguous.

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

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

Provides clear context for when to use (when reporting issues) and instructs to include the conversation array for reproduction. It does not explicitly name alternatives, but sibling tools are clearly unrelated, so usage context is sufficient.

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. The description adds no new behavioral context beyond stating that it shows versions, but it is consistent with the annotations, so no contradiction.

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 that is clear, front-loaded, and free of unnecessary words. Every word contributes to the purpose.

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, no-output-schema tool, the description fully conveys what information is returned (platform and adapter versions). Annotations cover safety, making the description complete in 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?

The tool has no parameters and the schema description coverage is 100% (empty properties object). The description needs no parameter explanation, so the baseline score of 4 for a zero-parameter tool 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 uses a specific verb 'Show' with a clear resource 'current MCP platform and adapter versions,' distinguishing it from sibling tools like toolkit_info. It clearly states 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 purpose implies when to use the tool (when version information is needed), but no explicit when-to-use or when-not-to-use guidance is provided. For a zero-parameter tool this is acceptable, but there is no explicit alternatives comparison.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows it's safe. The description adds the type of data returned (connection status implies live checks) without overpromising. It stays consistent with the read-only nature.

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, well-structured sentence that front-loads the purpose and then lists the exact components returned. No wasted words or tautology.

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 stateless, zero-parameter tool, the description fully covers what the agent needs to know: what information is returned and what it represents. No output schema exists, but the description enumerates the key data points, making it complete for its simplicity.

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

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

The tool has zero parameters, and the description correctly omits any parameter explanations. Per rubric, 0 params grants a baseline of 4. No additional 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 clearly states the tool returns 'current toolkit state' and enumerates exactly what it includes (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from siblings like show_version (version info) and marketplace (available tools), making the purpose unambiguous.

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

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

The description implies this is the go-to tool for inspecting toolkit state, but does not explicitly contrast with alternatives or state when not to use it. Given the sibling list, the context is clear enough, but explicit exclusions are missing.

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?

Apesar das anotações indicarem somente leitura, a descrição adiciona transparência ao revelar que é um serviço pago com crédito pré-pago, que não envolve dados sigilosos e que o cliente é controlador dos dados (LGPD). Isso vai além das anotações.

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 relativamente concisa, mas repete a ideia de 'consulta em fonte oficial' em duas frases. Estruturalmente é um bloco único, sem separação lógica, mas não é excessivamente longo.

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?

Faltam detalhes essenciais: não explica o formato da resposta (não há schema de saída), não detalha os parâmetros, nem menciona possíveis erros ou pré-requisitos além do pagamento. A menção à LGPD e à oficialidade ajuda, mas não cobre a complexidade do esquema.

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

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

O esquema possui 14 parâmetros sem descrições, e a descrição da ferramenta não explica o propósito de nenhum deles. A cobertura do esquema é 0%, deixando o agente sem orientação sobre como preencher os campos.

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 declara claramente que a ferramenta realiza uma consulta de certidão cível de 1º grau no TJSP em fonte oficial. A ação (consultar) e o recurso (certidão cível) são específicos, embora não detalhe o que retorna.

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

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

Não fornece orientações sobre quando usar esta ferramenta em relação a alternativas. Menciona apenas que é uma consulta em fonte oficial e não aborda cenários de uso ou diferenciação de outras ferramentas.

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