PEP (Pessoa Exposta Politicamente)

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

Discloses behavior beyond annotations: two authentication modes with different persistence (permanent vs session-only), and that no-args returns a login link. This complements the idempotentHint and non-destructive annotations without 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 long sentence, slightly dense, but every clause carries essential information (config method, session method, no-arg behavior). It could be structured with bullet points, but remains efficient and readable.

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 minimal schema and no output schema, the description covers both login flows, token formats, and the no-argument behavior. The agent can correctly invoke the tool for either permanent or session authentication without ambiguity.

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 a string with no description, but the description fully explains it as the JWT pasted by the user, and clarifies that omitting the token triggers a link response. This compensates for the 0% schema 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 states the tool's purpose: authenticating to MCP.AI for IDE agents. It specifies the exact process (log in, copy token) and the two invocation modes, making it distinct from sibling tools like 'connect' or 'marketplace'.

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?

Explicitly recommends the config header approach for a permanent, non-expiring connection and contrasts it with the session-only token paste method. This gives clear when-to-use guidance and prioritizes the best option.

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, covering the safety profile. The description adds useful behavioral detail by explaining the two possible return states (authenticated:true with empty pending[] vs. missing credentials returning connect_url), which is context beyond 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?

Two sentences with no redundancy: the first sentence states the core purpose, the second adds conditional details. Information is front-loaded and every word 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?

Given zero parameters and no output schema, the description fully covers the tool's behavior by describing both output scenarios. It is self-contained and leaves no significant gaps for such a simple 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?

The tool has zero parameters, so the schema is trivially complete. The description appropriately explains the tool's behavior without needing to document any parameters, earning the baseline score for no-parameter tools.

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 the specific verb 'Returns' and identifies the resource as 'connection status and URLs', making the tool's purpose immediately clear. It distinguishes from sibling tools like 'authenticate' by focusing on status/URL retrieval rather than authentication actions.

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 when to use the tool: to check connection status and retrieve URLs. It does not explicitly contrast with alternatives like 'authenticate', but the conditional scenarios (all connected vs. missing credentials) imply the appropriate use case without being misleading.

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?

Beyond the annotations (readOnlyHint: false, openWorldHint: true, etc.), the description adds rich behavioral context: invoke works even when the MCP is not installed, returns connect/checkout links for credential/payment issues, and notes that write actions require workspace owner/admin. It also reveals that invoke performs a behind-the-scenes one-off install. No contradictions with annotations 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 long (multiple sentences) but logically structured: it starts with the core purpose and flow, then covers important behaviors, usage guidance, and the prompt library. While some sentences could be tightened, each adds meaningful information for a tool with many actions and edge cases.

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 large parameter count (23) and no output schema, the description covers the essential workflow, authentication requirements, and prompt library thoroughly. It explains when to use which action and what to expect in terms of links and permissions. However, it omits some details like the 'resume' action and the 'immediate' parameter, preventing a perfect score.

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, but the description compensates by explaining the meaning of the 'action' enum values and the core workflow (search, describe, invoke, install, prompt functions). It gives context for parameters like mcp_id, tool_id, arguments, and prompt_vars. However, it does not explain many parameters (limit, immediate, tier_slug, cancel_reason, etc.), leaving some gaps in semantic understanding.

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 that the tool is 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It identifies a specific resource and function, while distinguishing itself from sibling tools by being the central hub for discovery and execution. The explicit core flow (search → describe → invoke) reinforces its unique role.

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 when-to-use guidance: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use.' It also differentiates list_tools for what is currently callable, request_mcp for building new MCPs, and the prompt library functions for prompt text. This clearly directs the agent to the right action.

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 provide readOnlyHint, idempotentHint, and destructiveHint=false. The description adds meaningful context beyond that: 'Consulta informação de ACESSO PÚBLICO em bases e fontes oficiais', 'sem credenciais', and LGPD responsibilities. This clarifies data origin and legal framing, complementing the annotations without 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 consists of three sentences, each adding value: purpose, payment/access, and data/legal nature. It is front-loaded with the primary purpose and avoids fluff, though it includes extras like 'Hospedado pela plataforma' that are not strictly necessary. Overall, it is concise for the information conveyed.

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 tool with no output schema and safety annotations, the description covers essential aspects: purpose, data source, payment, and legal responsibility. However, it omits semantics of the 'completo' parameter and any guidance on output or error handling. This is a moderate gap given the tool's compliance context, but acceptable for a simple lookup.

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 carry the burden. It explains the essential CPF parameter via 'a partir do CPF', but the optional boolean 'completo' is not explained at all. This leaves the parameter ambiguous, and the description only partially compensates for missing schema 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 the tool's purpose: 'Verifica se uma pessoa é Politicamente Exposta (PEP) a partir do CPF' – a specific verb (verifica) and resource (CPF) with the domain context of compliance/AML. It distinguishes itself from unrelated sibling tools (system utilities) by naming the unique PEP-checking capability.

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 when to use the tool: 'para diligência de compliance e AML' (for compliance and AML due diligence). It also mentions payment model and public data access, giving operational context. However, it does not explicitly name alternatives or exclusion cases, though siblings are not alternatives.

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 idempotentHint=true and destructiveHint=false, covering the safety profile. The description adds the requirement to include conversation context for reproduction but doesn't elaborate on side effects or expected outcomes, which is acceptable given the 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 two sentences with no filler: the first states the purpose, the second gives a specific usage directive. 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 reporting tool with one required parameter and no output schema, the description covers essential usage and reproduction guidance. A brief note on what happens after submission would make it more complete, but the current description is adequate for an AI agent to select and invoke the tool 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?

Schema description coverage is 0%, so the description must compensate. It explicitly explains the conversation parameter's purpose (recent messages for reproduction) and implies message is the report content, but the context parameter remains undocumented. Partial compensation for two out of three parameters warrants a score of 3.

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 reports bugs, missing features, or feedback, using specific verbs and resource categories. It distinguishes itself from sibling tools by addressing a unique action not covered by authenticate, connect, marketplace, etc.

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 usage context by instructing users to include the conversation array with recent messages for reproduction. While it doesn't explicitly name alternatives or exclusions, no sibling tool offers a similar reporting function, so the guidance 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, covering the safety profile. The description adds that both platform and adapter versions are shown, providing slightly more context about the tool's scope without contradicting 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?

The description is a single, focused sentence that conveys all necessary information without any filler. It is extremely concise while remaining complete and clear.

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, and rich annotations, the description is fully complete. It states exactly what the tool does and there are no edge cases or return-value complications that need elaboration. The output is inherently obvious (version strings), so no additional detail is required.

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 schema provides complete coverage. The baseline for no parameters is 4; the description does not need to add parameter information as there are none to explain.

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 ('show') and resource ('current MCP platform and adapter versions'), which distinguishes it from sibling tools like 'authenticate' or 'marketplace'. This is a precise and unambiguous purpose statement.

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?

While the description does not explicitly state when to use versus alternatives, the purpose itself makes the usage context clear—users needing version information would invoke this tool. No exclusions or alternative suggestions are needed given the tool's simplicity and distinct purpose.

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's main contribution is specifying the output content. It reveals that the tool returns the connected accounts per MCP and the count of catalog tools, adding behavioral context beyond the safety hint without contradicting 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?

The description is a single sentence that front-loads the core action ('Returns the current toolkit state') and then efficiently lists the specific data points. Every word adds value, and the sentence is easy to scan, making it ideal for an agent parsing tool descriptions.

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 read-only status tool, the description covers the key return categories: installed MCPs, connection status, accounts, and catalog tool counts. It does not specify the exact output format or field names, but given the simple nature and no output schema, this is sufficiently complete to set correct 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?

The tool has zero parameters, and the empty schema fully documents the input surface. Since there are no parameters to explain, the description does not need to add parameter semantics. The baseline for 0-param tools is 4, and the description meets that by not inventing unnecessary input requirements.

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 with a specific verb ('Returns') and resource ('current toolkit state'), and enumerates the exact data points it provides (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from sibling tools focused on actions like authenticate, connect, or marketplace, making its function 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 no explicit guidance on when to use this tool versus alternatives. There is no mention of when to choose this over show_version or other informational tools, nor any conditions or prerequisites. The usage context is only implied by the function's nature as a status inspection tool, which is insufficient for optimal tool selection.

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