Proibidos BACEN

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

Annotations indicate idempotent and non-destructive behavior. The description adds context about session permanence, the browser login flow, and the two call variants (with/without token), but does not detail potential side effects like token storage or response format.

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 informative but slightly verbose, with a long first sentence combining multiple instructions. It could be split but remains readable and all content is relevant.

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 auth tool with one optional parameter and no output schema, the description covers the main usage scenarios and permanence trade-off. It lacks explicit return value details, but the essential information is present.

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 provides no description for the token parameter, but the description fully explains it: the token is a JWT that the user pastes, and calling with no args retrieves the link. 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: to authenticate with MCP.AI for IDE agents by logging in and obtaining an access token. It distinguishes two usage modes (permanent config vs session-only token) and gives concrete steps.

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?

Explicit guidance is provided: recommends adding the token to server config for a permanent connection, or passing it as a JWT for session-only login, with no-args to fetch the link. This clarifies when to use each approach.

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 readOnly and idempotent hints. The description adds valuable behavioral context: the data is public, no authentication is needed, there is a cost per query, and the client is the data controller under LGPD. This significantly exceeds the annotation information and has 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 concise three-sentence paragraph. The first sentence states the core purpose, and the other sentences add essential access and legal context without unnecessary fluff. Every sentence contributes new 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?

The tool is simple, and the description covers purpose, access model, cost, and legal context. However, it lacks any mention of the response format or what the output contains, and the unexplained 'completo' parameter leaves a gap. The schema required-parameter mismatch also adds confusion.

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 explains that CPF or CNPJ are the lookup identifiers, but it doesn't clarify the 'completo' parameter at all. Moreover, it says 'CPF ou CNPJ' while the schema marks both as required, creating ambiguity about whether one or both must be supplied.

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 ('verifica se consta') and resource ('Quadro Geral de Proibidos do Banco Central'), and identifies the input identifiers (CPF/CNPJ). It is easily distinguishable from the unrelated sibling tools.

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 useful context for when to use the tool: it requires no credentials, costs prepaid credit, accesses public data, and has LGPD responsibilities. It doesn't explicitly exclude alternatives, but the sibling tools are unrelated, so this is acceptable.

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?

Description discloses response shapes based on connection state (all connected vs credentials missing), which adds value beyond the readOnlyHint and idempotentHint annotations. However, it doesn't address partial connection states or error scenarios.

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 with a clear structure: what it returns and outcome variants. No 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 zero-parameter, read-only status tool, the description covers core behavior and key response cases. Gaps: partial connection states and what 'per-install URLs' exactly means, but overall sufficient.

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 takes 0 parameters. Schema is empty and coverage is 100%. Baseline 4 applies since no params need explanation. Description adds no param info but not 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?

Description clearly states 'Returns connection status and URLs' with specific conditional outcomes. It distinguishes from sibling 'authenticate' by focusing on status reporting rather than action, 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 when to use (to check connection status or get connect URL) but does not explicitly name alternatives or state when not to use it. Context is clear but 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?

Beyond the sparse annotations, the description reveals that invoke can run tools without installing them, returns connect or checkout links for auth/payment, and that all writes require workspace owner/admin. It also mentions installed_in_toolkit vs installed_in_workspace flags, providing valuable behavioral context.

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?

Although lengthy, the description is packed with distinct, necessary concepts: marketplace catalog, core flow, one-off invoke semantics, auth/payment links, install vs invoke, permission requirements, and the prompt library. The information density is high 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?

The description thoroughly covers the main MCP marketplace workflow and most key actions, but it omits the 'resume' action and gives no explanation for prompt-library parameters or administrative fields like immediate and tier_slug. Given the tool's complexity and the absence of an output schema, these gaps mean it 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?

With 0% schema description coverage, the description takes on the burden of explaining parameters. It gives meaning to the action enum and implies roles for mcp_id, tool_id, and arguments through the core flow. However, many parameters (prompt_slug, prompt_vars, conversation, immediate, tier_slug, etc.) remain undefined, leaving the full 23-parameter surface only partially explained.

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 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' clearly identifying the tool as both a catalog and an execution runtime. It then enumerates the core flow (search → describe → invoke) and lists all sub-actions, distinguishing it from sibling tools like authenticate and toolkit_info.

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 instructs when to use invoke vs install: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT.' It also clarifies the roles of list_tools, request_mcp, and report_bug, providing direct guidance for choosing among 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, establishing that the operation is safe to repeat and non-destructive. The description adds little beyond purpose, only suggesting including conversation for reproduction. It does not contradict any annotations, but it also does not disclose additional behavioral traits such as side effects or authentication needs.

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, succinct and front-loaded with the primary purpose. It contains no redundant phrases and conveys the key instruction about conversation inclusion. 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 tool with three parameters and no output schema, the description is only partially complete. It explains the purpose and the conversation parameter, but leaves the required message parameter and context unspecified. An agent could infer the message is the bug/feedback text, but additional guidance would improve completeness.

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 references the 'conversation array' and its purpose (recent messages for reproduction), which adds some meaning to the conversation parameter. However, it does not describe the required 'message' parameter or the optional 'context' parameter, leaving significant gaps. The term 'array' conflicts with the schema's string type, though it might imply a serialized array.

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's purpose: 'Report a bug, missing feature, or send feedback.' The verb 'report' is specific, and the resource targets are explicit. Among sibling tools (authenticate, connect, marketplace, etc.), none overlap with bug/feedback reporting, so it is well-distinguished.

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: 'Report a bug, missing feature, or send feedback.' It also instructs to 'Include the conversation array with recent messages for reproduction,' which is a practical usage directive. However, it does not explicitly mention exclusions or alternatives, though sibling tools are unrelated.

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 the scope 'current' and specifies both platform and adapter versions, which gives a bit more context than the annotations alone. 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 a single concise sentence: 'Show the current MCP platform and adapter versions.' It front-loads the verb and resource, includes no filler, and every word carries meaning.

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 tool with safety annotations, the description fully explains the tool's functionality. No output schema exists, but the return value (version numbers) is implicit from the description. All necessary context is provided for an agent to use 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 tool has zero parameters, and the input schema is an empty object, meaning schema description coverage is 100%. The description does not (and need not) mention parameters. Per the rule, a zero-parameter tool gets a baseline of 4, and the description adds no extra parameter info (none 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 uses a specific verb 'Show' and identifies the resource as 'MCP platform and adapter versions,' clearly indicating what the tool does. It distinguishes itself from siblings like authenticate, connect, and report_bug, and even from toolkit_info by specifying version info rather than general tool information.

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 explicit guidance is given on when to use this tool versus alternatives like toolkit_info. However, the tool's purpose is self-evident for checking platform/adapter versions, so usage context is implied. The lack of explicit exclusion or alternative naming prevents a higher score.

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 safety profile is covered. The description adds valuable behavioral detail by listing the specific state information returned, which is especially important given the absence of an output schema.

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 action ('Returns') and then lists the return components in a clear sequence. Every word contributes meaningful information without waste.

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 read-only state tool with no parameters and no output schema, the description fully covers the return payload and purpose. It addresses the key information an agent would need: what data is available and the scope of the toolkit state.

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 zero parameters, the baseline is 4. The description adds no parameter-specific meaning because there are none to explain, and the empty input schema requires no further clarification.

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 the current toolkit state' and enumerates exact contents: installed MCPs, connection status, connected accounts, and catalog tool counts. This specific verb+resource definition distinguishes it from siblings like show_version, which likely only returns version information.

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 communicates when to use the tool: whenever an agent needs an overview of installed MCPs, their connection status, and catalog tool counts. It provides clear context but does not explicitly name alternatives or exclusion criteria, so it falls short of a 5.

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