Conselho Nacional de Justiça: Improbidade Administrativa e Inelegibilidade

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

Annotations indicate idempotentHint=true and destructiveHint=false, which are already safe. The description adds behavioral context: calling with no args returns a login link, calling with a token establishes a session-only login, and the token does not expire when placed in server config as a header. This gives the agent meaningful behavioral expectations beyond 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 information-rich and front-loaded with the target context and the essential action. It is slightly run-on with multiple alternatives packed into one long sentence, but every clause contributes necessary behavioral information, so it is appropriately concise overall.

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 single optional parameter, no output schema, and no schema descriptions, the description does enough to completely convey the authentication flow: configuration setup, session-only fallback, and link generation behavior. It does not explicitly say when authentication becomes necessary, but the IDE-agent framing is sufficient practical 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 schema has only an optional `token` string with no description, but the description fills the gap by explaining that `token` is a JWT access token pasted by the user and is only used for session-only login. It also clarifies that omitting token triggers a link-returning behavior, giving the single parameter useful semantic context.

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 does: authenticates to MCP.AI by obtaining and providing an access token, either persistently via config or session-only via pasted token. The verb 'log in' and 'authenticate' plus the concrete resource (access token for this server's config) make the purpose unmistakable.

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

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

The description gives explicit usage guidance: it is for IDE agents like Cursor, provides a best-practice config approach for permanent login, and clarifies when to paste a token versus call with no args to get the link. It also distinguishes session-only from permanent authentication 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 indicate read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond annotations: cost per query (prepaid credit), no platform credentials required, data is non-confidential, and the client is the data controller under LGPD. This enriches the agent's understanding of operational and legal boundaries.

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 composed of three sentences, each providing relevant operational or legal context. It is front-loaded with the core purpose and then adds cost and compliance details. Slightly verbose due to LGPD phrasing, but still concise and organized.

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 (read-only query with optional parameters). The description covers the data source, cost, and legal responsibility, but lacks guidance on parameter usage and expected output format. Since there is no output schema, the description should have provided some insight into return values, but it does not. It is adequate but with 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?

The input schema has three parameters (cpf, cnpj, nome) with 0% description coverage, and the description does not mention any of them. There is no guidance on how to use these parameters or whether they are mutually exclusive. The description fails to add meaning beyond the schema, leaving the agent without necessary parameter semantics.

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: querying official CNJ data on Improbidade Administrativa and Inelegibilidade. It uses a specific verb ('consulta') and names the resource (Conselho Nacional de Justiça), distinguishing it from the sibling tools which are generic platform operations.

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 this tool: for querying official Brazilian sources, with prepaid credits and no platform credentials. It doesn't explicitly state when not to use it or mention alternatives, but the sibling tools are unrelated, so the 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 and idempotentHint, so the safe, non-destructive behavior is covered. The description adds transparency about the two possible output states and what happens when credentials are missing, without overstating 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 two sentences, front-loads the core result, and uses each sentence to convey a meaningful distinction. There is no unnecessary detail 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?

For a read-only status tool with no parameters and no output schema, the description gives the key return states and associated URLs. It is nearly complete, though it does not explicitly describe a mixed/partial provider connection state beyond the all-connected and credentials-missing 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 tool has zero parameters, so parameter-level semantics are not applicable. The description still helps by explaining what behavior the parameterless call produces, which is sufficient in this case.

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 connection status and URLs, and gives concrete conditional behavior (authenticated:true vs connect_url). This distinguishes it from siblings like authenticate, which is associated with performing authentication rather than reporting status.

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 it should be used to check connection status and retrieve URLs when credentials are missing, which is useful but not explicitly framed as when-to-use guidance. It does not mention exclusions or explicitly reference an alternative such as authenticate.

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?

Given annotations only state readOnlyHint false, the description adds essential behavioral context: invoke works even without installation, returns connect/checkout links for credentials/payment, and writes require owner/admin. It also explains flags for installed status and the prompt library's share links, far exceeding annotation coverage.

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 long but logically structured, leading with the core flow and then addressing specific behaviors and the prompt library. Each sentence contributes necessary information, though chunking into a single paragraph reduces scannability. It is appropriately detailed for a tool with 14 distinct actions.

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 (23 parameters, no output schema), the description covers the primary use cases, retry logic, and permissions thoroughly. It omits some edge-case parameters but provides enough context for an agent to operate the most common actions correctly. The absence of output schema is mitigated by describing typical responses like connect and checkout links.

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 compensates by explaining the meaning of key parameters like action, query, mcp_id, tool_id, arguments, and prompt_* fields. It does not detail every parameter (e.g., limit, immediate, cancel_reason), but the core flow is well documented, so it adds significant value 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 clearly states the tool's role as the official marketplace and catalog of MCPs/tools, with a specific flow for discovery, describe, and invoke. It distinguishes itself from sibling tools by covering the entire lifecycle, and the term 'marketplace' is given a concrete operational definition.

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 explicitly outlines when to use each action (search, describe, invoke, install, list_tools, etc.) and provides decision rules such as preferring invoke for one-off use and install for permanence. It also contrasts with alternatives like request_mcp and clarifies subscription handling.

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 indicate readOnlyHint=false (so it may have side effects) and destructiveHint=false (not destructive), idempotentHint=true (safe to repeat). The description adds that it sends a bug report/feedback, implying a network call, but does not disclose what happens after submission, potential rate limits, or whether it guarantees a response. With annotations present, the description adds a bit of context but not rich behavioral detail.

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, concise, and front-loaded with the core purpose. It includes the key instruction about the conversation array without wasted words. Perfectly 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?

Given the tool has 3 parameters, 0% schema description coverage, no output schema, and moderate annotations, the description should compensate. It fails to explain the 'context' parameter, the JSON format of 'conversation', and the expected message content. The description is too thin for an agent to invoke correctly without additional guessing. Sibling tools are unrelated, so no comparison helps. It is incomplete for a functional report 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 0%, meaning the description must explain parameters. The description mentions 'conversation' as a concept and 'message' implicitly (report a bug), but it does not clarify the role of 'context' or the format of 'conversation' (it says 'array' but does not explain what it should contain). The default values are not explained. Thus, the description provides minimal semantic help for 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 tool's purpose: report a bug, missing feature, or send feedback. It also adds the specific instruction to include the conversation array for reproduction. This distinguishes it from siblings (which are unrelated actions like authenticate, connect, etc.), though it doesn't explicitly differentiate from any similar reporting 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 when to use it (when there's a bug, missing feature, or feedback) and gives a specific instruction to include the conversation array. However, it does not specify when not to use it or alternatives, and there is no mention of any prerequisites or context requirements beyond the conversation array. Adequate but not 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, aligning with the non-mutating 'Show' action. The description adds the specific detail that both 'platform' and 'adapter' versions are returned, which is mildly informative beyond the annotations but does not disclose additional behaviors like output format or potential latency.

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

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

A single, front-loaded sentence with no wasted words. Every word earns its place, and the structure is optimally 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 zero-parameter, read-only version inquiry with strong annotations, the description fully covers the necessary context. The tool is trivial, 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?

There are zero parameters, and the rubric specifies a baseline of 4 for such cases. The description needs to add no parameter meaning since none exist.

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 verb 'Show' and the resource 'MCP platform and adapter versions,' making its purpose unambiguous. However, it does not explicitly distinguish itself from sibling tools, though its simplicity largely removes ambiguity.

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 tool is used when you need version information, but it provides no explicit guidance on when to use it over alternatives or any exclusions. For such a trivial tool, the implied usage is acceptable but not explicitly stated.

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 agent knows it is a safe, non-mutating operation. The description adds value by specifying what the read returns (installed MCPs, connection status, accounts, tool counts), which complements the annotations. There is no contradiction. It could have mentioned whether the call has side effects like network probing, but for a lightweight status query, 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 a single, front-loaded sentence that packs all relevant information without fluff. Every clause adds value: 'current toolkit state', 'installed MCPs', 'connection status', 'accounts connected', 'catalog tools count'. It is concise and well-structured.

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 (no parameters, no output schema, readOnlyHint=true), the description is complete enough. It tells the agent exactly what information it will get. It might have mentioned the response format or type, but since there is no output schema, the agent relies on the description, and the listed contents are clear. The sibling context also suggests this is a status/diagnostic tool, which fits.

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 description coverage is 100% (trivially, since there are no properties). The description does not need to explain any parameters. The baseline for zero-param tools is a 4, and the description does not waste space on parameters, so a 4 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 tool returns current toolkit state and enumerates specific contents: installed MCPs, connection status, accounts, and catalog tool counts. It uses a specific verb ('Returns') and resource ('current toolkit state'), which distinguishes it from siblings like connect, authenticate, and show_version.

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 a diagnostics/status tool for inspecting the toolkit's connected state, useful before using connect or authenticate. However, it does not explicitly state when to use it versus siblings or when not to use it. The context signals show zero parameters and readOnlyHint=true, reinforcing it as a status query, but explicit guidance is absent.

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