CGU (Controladoria Geral da União)

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

The description discloses behavioral traits beyond annotations: the permanent vs. session-only distinction, the requirement to login in the browser, and that no args returns a link. Annotations already indicate idempotency and non-destructiveness, and the description adds useful context 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 concise and tightly structured, using a colon and alternatives to front-load the tool's purpose. Every sentence conveys necessary information about configuration, session login, and the no-arg behavior.

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 the key use cases and the return behavior (link vs. session). Lacking an output schema, it adequately describes what the tool does, though it doesn't explicitly state error handling or the exact response after successful token submission.

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 one optional string parameter with no description (0% coverage). The description fully compensates by explaining the token parameter: 'call with { token: "<jwt>" } after the user pastes' and 'with no args to get the 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 indicates this tool enables authentication to MCP.AI for IDE agents, including the browser login flow and token handling. However, it does not explicitly distinguish it from sibling tools like 'connect' or specify when not to use it.

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 explicit usage instructions: the recommended permanent approach via config header, a session-only login by passing a token, and getting the login link with no arguments. It also states the trigger ('after the user pastes') for using the token parameter.

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, idempotent, non-destructive. Description adds operational details: hosted by platform, no credentials, prepaid credit cost, data is public not private, and LGPD data controller responsibility. These go beyond annotation hints and are consistent with them. 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?

Three sentences, each adds unique information: purpose, payment/credentials, and data legal context. The first sentence is the core purpose, followed by necessary operational details. Slightly long due to LGPD clause, but 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?

Despite annotations, the tool has 4 parameters and no output schema. Description provides high-level context (public data, cost, no credentials) but leaves critical parameter semantics unexplained and does not describe what result records contain. An agent would struggle to correctly invoke this tool without additional information.

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 description must compensate. It only explains Cpf/Cnpj as identifiers, but fails to clarify 'Tipo' or 'completo'. Additionally, it says 'a partir do CPF ou CNPJ' while the schema requires both Cpf and Cnpj, creating confusion about how to fill them. This is insufficient for correct invocation.

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 tool queries records of a person or company at CGU using CPF or CNPJ. This is a specific verb ('consulta') + resource ('registros na CGU') and stands out from unrelated sibling tools like authenticate 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?

Provides clear context: use when needing CGU public data, no credentials required, pay per query with prepaid credit. It does not explicitly name alternatives, but sibling tools are unrelated, so no alternative is needed. The context is sufficient for an agent to decide when 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 readOnlyHint=true and idempotentHint=true. The description adds meaningful behavioral detail: it explains the output states for connected vs. missing credentials, including the exact fields returned. This helps the agent anticipate results, though it doesn't cover all possible states.

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 with no filler. It front-loads the primary purpose ('Returns connection status and URLs') then elaborates on behavior.

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 params, no output schema), the description covers what the tool does and its key output variations. It's sufficient for an agent to know when and how to invoke it.

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 description has no need to explain parameter syntax. The schema is empty and the baseline for 0 params is 4. The description adds no parameter info, but none is 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 connection status and URLs, with specific behavior for two conditions. This distinguishes it from sibling tools like 'authenticate' which likely initiates authentication. No 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 the tool is for checking connection status, but doesn't explicitly state when to use it versus 'authenticate' or other siblings. No alternatives or exclusions are mentioned. It's functional but lacks explicit guidance.

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, the description discloses important behaviors: invoke works even when the MCP is not installed, one-off installs do not bloat the toolkit, auth/payment failures return connect or checkout links that require retry, and writes require owner/admin. It also explains installed_in_toolkit vs installed_in_workspace flags and the prompt library's login-free share links, adding substantial non-obvious 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?

The description is dense and lengthy, but this is largely justified by the tool's 14 distinct actions and complex invoke/install distinction. It is organized by core flow, key behavior, usage preference, auth, and prompt library, and almost every sentence adds needed information; a little repetition and the single long paragraph prevent a perfect score.

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 high complexity, 23 parameters, and no output schema, the description covers the essential workflow, auth/ownership requirements, billing interactions, retry logic, and the prompt library sub-system. It does not fully specify return value shapes for search/list_tools or detail all parameter combinations, but it provides enough context for a capable agent to navigate the 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?

With 0% schema coverage, the description carries significant burden and does clarify the meaning of action, mcp_id/tool_id, invoke behavior, and prompt-related parameters. However, many parameters remain unexplained—limit, immediate, tier_slug, cancel_reason, cancel_comment, conversation, request_details, prompt_targets, and several others—leaving gaps an agent would need to guess at.

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 marketplace as the official MCP/tool catalog and execution runner, with a core search → describe → invoke flow plus prompt library functions. It distinguishes itself from siblings by naming the platform and explaining its unique multi-action role, though the purpose is spread across many actions rather than a single verb+resource.

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 guidance: prefer invoke for one-off use, use install only when permanent toolkit membership is desired, use request_mcp when nothing fits, and use list_tools to see what is callable now. It also states when writes require owner/admin and how credentials/payment link flows work, making alternatives and conditions 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=false, destructiveHint=false, and idempotentHint=true, covering the basic safety profile. The description adds that the tool forwards bug reports and that the conversation parameter aids reproduction. However, it does not clarify what side effects occur (e.g., creating a ticket) or whether authentication is required, leaving some behavioral ambiguity.

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-loaded with the primary purpose. The second sentence gives a specific, actionable instruction about the conversation parameter. There is no unnecessary detail, making it highly 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?

The tool is relatively simple, and the description covers the core action and one key parameter. However, it omits information about expected return values, prerequisites like authentication (given the sibling authenticate tool), and the purpose of the context parameter. These gaps are notable given there is no output schema to compensate.

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 parameter meaning. It explains that 'conversation' should contain recent messages for reproduction, but does not explain 'message' (the required parameter) or 'context'. The description also calls 'conversation' an array while the schema types it as string, which could cause confusion. Overall, only one of three parameters receives meaningful elaboration.

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 ('Report') and identifies the resources ('bug, missing feature, or send feedback'). This clearly distinguishes it from sibling tools like show_version and marketplace, leaving no ambiguity about its purpose.

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 states the use case: to report a bug, missing feature, or provide feedback. It also gives a directive to include the conversation array for reproduction. No alternative tools are mentioned, but none are needed since no other sibling handles issue submission, so the context is 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?

The description is consistent with annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false). It adds minimal extra context ('current' suggests live retrieval), but relies on annotations for behavioral safety. Does not disclose return format or potential errors, though this is a simple read-only tool.

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 concise sentence that is front-loaded with the verb and resource. Every word contributes meaning; no filler or 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 no-parameter, read-only version check, the description is complete. It explains exactly what the tool shows without needing details on parameters or return types. Sibling context does not introduce 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 tool has zero parameters, so the schema fully covers all inputs (vacuously). The description adds no parameter-specific semantics; the baseline for 0 parameters 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 the tool's function with a specific verb ('show') and resource ('MCP platform and adapter versions'). It is unambiguous and distinguishes itself from siblings like authenticate, connect, and toolkit_info, which serve 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?

Usage is implied: use when you need the current platform and adapter versions. However, no explicit guidance is given on when not to use it or how it differs from sibling tools like toolkit_info, which might also provide version-related information.

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, idempotentHint, and destructiveHint, covering safety. The description adds value by detailing exactly what state will be returned, which helps the agent understand the scope without repeating annotation data.

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 and lists the key components. Every word earns its place with no redundant or vague phrasing.

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 info tool with no output schema, the description fully conveys what the agent needs to know: it returns the toolkit state with the specified details. Annotations cover safety, so no further disclosure is needed.

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 baseline is 4 per the rubric. The description adds no parameter info, but none is 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 the specific verb 'Returns' and clearly identifies the resource: toolkit state, including installed MCPs, connection status, connected accounts, and catalog counts. This clearly separates it from action-oriented siblings like connect and authenticate.

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 makes the use case evident—use this to inspect toolkit state—and implies it is the go-to for status queries. It does not explicitly name alternatives or exclusions, but the context is clear enough given the sibling tools.

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