MPT RJ: Certidão Negativa de Feitos

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

The description adds behavioral context beyond the annotations by explaining that a token passed here only creates a session-only login, while config-based tokens provide a permanent non-expiring connection. Annotations already communicate idempotency and non-destructiveness, and the description aligns with them. It could further clarify what happens after successful authentication, but coverage is still solid.

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 reasonably concise at about three sentences, with the key information front-loaded: what the tool is and the basic login flow. It each sentence adds necessary procedural detail, though the phrasing 'MCP.AI for IDE agents' and 'log in in the browser' is a bit awkward and could be tightened.

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 one simple optional parameter and no output schema, the description is almost complete for call semantics. It effectively covers the two invocation modes (token/no token), the permanent-config alternative, and the source of the token. It would be slightly stronger if it explicitly stated what the function returns, but it in the context of a simple auth tool, the coverage is strong.

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 provides the parameter name 'token' as an optional string, with zero description coverage. The description fully compensates by clarifying that the token is a JWT pasted by the user, and by explaining the two modes: call with '{ token: "<jwt>" }' or call with no arguments to get a login link.

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 tool as the MCP.AI authentication endpoint for IDE agents, explaining it can log in via browser, provide a link, or accept a token for session-only login. It is specific about the verb+resource (authenticate with token/link), but it does not explicitly contrast with the sibling 'connect' tool, so it stops short of fully distinguishing 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 explicitly explains when to use the tool: with no args to obtain a login link, or with a pasted token for session-only authentication. It also gives the alternative of adding the token to the server config as a permanent header, making the use-vs-alternative distinction 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 and idempotentHint=true, so the safety profile is known. The description adds context about the response states (authenticated vs. pending) and mentions that it returns URLs when credentials are missing, which is useful beyond annotations. However, it doesn't describe any side effects beyond what's implied by readOnly, which is fine.

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, well-structured, and front-loaded. It states the main purpose first, then provides conditional logic. Every word earns its place, no 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 simple status tool with no parameters, the description is quite complete. It explains response states and URL conditions. There's no output schema, but the description partly compensates by describing the response fields (authenticated, pending, connect_url). It could mention whether it returns other fields or the format, but it's adequate for the tool's 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 schema coverage is 100% (it's empty). Per the instructions, baseline is 4 for 0 params. The description adds value by explaining what the absence of parameters means: it's a status check with no inputs 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 what the tool does: it returns connection status and URLs, with specific details about the response structure (authenticated, pending, connect_url). However, it doesn't explicitly distinguish from siblings like 'authenticate' or 'marketplace', but the purpose is clear enough.

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: it's for checking connection status, and it explains what happens when credentials are missing. But it doesn't explicitly say when to use this vs. 'authenticate' (which presumably initiates connection). No exclusions or alternatives are named, so it's 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?

The description adds substantial behavioral context beyond the annotations: invoke runs one-off without installing or bloating the toolkit, credential needs return a connect link, empty wallets return a checkout/top-up link, and writes require workspace owner/admin. It also clarifies that invoke works even when the MCP is not installed. This does not contradict 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 long but every sentence earns its place given the 14-action multiplexed tool. It is front-loaded with the core purpose, uses a clear flow (search → describe → invoke), and separates key concerns: invoke behavior, install vs invoke, permissions, and the prompt library. The density is justified by the tool's complexity.

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, minimal annotations, and 14 actions, the description is remarkably complete: it covers the core flow, invoke edge cases, install vs invoke trade-offs, permission requirements, and the prompt-library sub-actions. It does not explicitly mention the 'resume' action or several prompt-related parameters, but the overall guidance is sufficient for an 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 carries the burden. It explains the central action parameter and gives meaning to tool_id, mcp_id, and invoke arguments through the flow narrative. However, with 23 parameters, many remain unexplained (immediate, tier_slug, prompt_targets, conversation, cancel_reason, etc.), so it compensates strongly but not completely.

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 opens with a specific identity: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then defines the core flow (search → describe → invoke) and explicitly names report_bug and request_mcp, distinguishing them from sibling tools. This is a clear verb+resource statement with sibling differentiation.

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 when-to-use guidance: 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT in the active toolkit'; 'list_tools lists what is callable right now'; 'report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits.' It also explains the prompt-library sub-actions and their distinct purposes.

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, idempotentHint, etc.), the description discloses the cost model (prepaid per query), the nature of the data (public, not confidential), and the LGPD responsibility of the client. This adds meaningful behavioral context without contradicting any 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 compact and front-loaded with the core purpose. It adds relevant operational and legal details in a structured way. The legal disclaimer about LGPD, while necessary, adds a bit of length, but overall it remains efficient.

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 purpose, cost, source, and legal aspects, but it omits any guidance on parameter usage (CPF/CNPJ) or expected return format. Since there is no output schema and no parameter descriptions, this is a notable completeness gap for a tool that still needs an identifier to execute.

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 includes 'cpf' and 'cnpj' with no property descriptions, and the tool description makes no mention of these parameters or how to use them. With schema description coverage at 0%, the description fails to clarify that one of these identifiers is presumably required for a certificate lookup, leaving the agent to infer parameter semantics from the parameter names alone.

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 specifies the action: consulta (query) of the 'Certidão Negativa de Feitos' (negative certificate of proceedings) from MPT RJ. It names the specific official source and resource, clearly distinguishing it from the unrelated sibling platform tools like authenticate and 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?

The description provides practical usage context: hosted by the platform, no platform credentials needed, and prepaid credit per query. While it doesn't explicitly contrast with alternatives, it gives enough guidance on when and how to use the tool, especially since sibling tools are platform-level utilities rather than alternate lookup methods.

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 idempotent, non-destructive, and not read-only. The description adds that conversation should be included for reproduction, which is useful context. However, it doesn't elaborate on side effects or requirements beyond that, so it meets but doesn't exceed the baseline given 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?

Two concise sentences, no fluff. The key instruction (include conversation) is front-loaded. 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?

Given the simplicity (no output schema, few parameters), the description covers the core purpose and a key usage detail. However, it doesn't clarify the format of message or context, and there's no note on response behavior, but that's acceptable for a simple feedback 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 coverage is 0% (no parameter descriptions in schema). The description mentions the conversation array but does not clarify the 'message' or 'context' parameters. The word 'message' is obvious but not explicitly explained, and 'context' is left ambiguous. This fails to compensate for the lack of 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 reports bugs, missing features, or feedback, and explicitly mentions including conversation for reproduction. This is specific and distinguishable from sibling tools like 'marketplace' or 'connect'.

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 tells when to use it (report issues) and what to include (conversation array). It doesn't explicitly state when not to use it or name alternatives, but the purpose is specific enough that an agent can infer appropriate usage.

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 annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the useful detail that results reflect 'current' versions, but it does not disclose additional behavioral traits such as output format or whether any network call is made. No contradiction with annotations exists.

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 action and scope with no wasted words. 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?

For a zero-parameter, read-only version inspection tool, this description is largely sufficient for an agent to select and invoke it correctly. Since there is no output schema, an explicit note about the returned version format or structure would have pushed it to a 5, but the current wording adequately communicates the tool's purpose and output content.

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 input schema is trivially complete, so the baseline of 4 applies. The description adds no parameter information, but none is needed because the schema leaves no ambiguity.

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 action ('Show') and the exact resource ('current MCP platform and adapter versions'). This specific scope distinguishes it from siblings like authenticate, connect, and marketplace, which serve entirely different purposes.

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 the tool—whenever version information is needed—but it does not explicitly state when to prefer it over alternatives or exclude any sibling tools. There is no mention of context, compatibility checks, or related tools such as toolkit_info.

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's safe. The description adds that it returns a snapshot of toolkit state, which is consistent with annotations. No additional behavioral quirks (e.g., freshness, latency) disclosed, but acceptable given annotations cover safety.

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, front-loaded with the verb 'Returns', and lists all key content. Zero wasted words; perfectly concise for a simple info 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?

For a zero-parameter info tool with strong annotations, the description fully covers what the tool does and what it returns. No output schema, but the description enumerates the return content. Complete enough for agents to use 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?

Tool has zero parameters, so schema coverage is effectively 100% by default. The description adds meaning by listing the content of the response (installed MCPs, connection status, accounts, catalog tools), which helps the agent know what it will get. Baseline for zero params is 4.

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: 'Returns the current toolkit state' and specifies the exact contents (installed MCPs, connection status, accounts, catalog tools). It is specific and distinct from siblings like authenticate, connect, or 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 usage as a diagnostic tool but does not explicitly state when to use it versus alternatives like show_version or marketplace. No exclusions or alternatives named, but the clear scope provides some context.

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