Portal da Transparência: Acordos de Leniência

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

Annotations already provide idempotentHint=true and destructiveHint=false. The description adds valuable behavioral context: the two authentication mechanisms (permanent config vs session-only token), the non-expiring nature of the config header, and the fact that calling with no args returns a login link. No contradictions 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 three sentences and information-dense, but every clause serves a purpose: identifying the audience, describing the login flow, presenting two authentication options, and giving the exact call signatures. It could be slightly more structured, but it is not bloated.

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 one optional parameter, no output schema, and existing annotations, this description is complete. It tells the agent exactly what to do (browser login, copy token), how to invoke the tool, what the two modes are, and what to expect (link or session). No 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 schema has one optional string parameter 'token' with no description. The description fully explains its semantics: pass { token: "<jwt>" } for session-only login, or omit it to receive the login link. This completely compensates for the schema's lack of parameter documentation.

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 IDE agents (like Cursor) to MCP.AI. It specifies the action (log in, copy access token), the resource (MCP.AI), and the target audience (IDE agents), distinguishing it 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?

The description provides explicit usage guidance: it recommends the best approach (config header for permanent connection) and an alternative (session-only login via pasted token). It also explains how to invoke the tool with or without the token. It doesn't explicitly contrast with sibling tools, but the context is clear enough 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, idempotentHint, and destructiveHint, so the safety profile is known. The description adds the conditional behavior of the tool (different return values based on connection state), providing context beyond annotations. It does not contradict any annotation and discloses key behavioral traits, so it gets a 4.

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 main purpose, and each sentence provides necessary elaboration. There is zero wasted wording, 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?

Given the tool's simplicity (0 params, no output schema, clear annotations), the description completely covers its behavior: it explains both return cases and the URLs. There is no missing context that would impede an agent's understanding of when or how to use 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?

The tool has zero parameters, so schema coverage is 100%. According to the guidelines, a baseline of 4 applies for 0 params. The description does not need to add parameter semantics because there are none, and it doesn't add anything that would be contradicted. It is a perfect score for the simple 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 further specifies the behavior for different conditions (all connected vs. missing credentials). This distinguishes it from siblings like 'authenticate' which likely handles the connection process. The specific verb 'returns' and resource 'connection status and URLs' make the purpose crystal clear.

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: 'When all providers are connected...' and 'When credentials are missing...' but it does not explicitly state when to use this tool vs alternatives or mention any exclusions. It provides context but lacks direct guidance on choosing it over other tools like 'authenticate' or 'toolkit_info'. Thus, it earns a 3 for implied 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 description discloses key behavioral traits beyond annotations: invoke runs tools even when not installed, may return connect/checkout links based on auth/payment status, requires workspace owner/admin for writes, and the effect of install on toolkit persistence. It even clarifies the prompt library's separate purpose. This goes far beyond the sparse 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, dense paragraph that, while informative, is long and could be broken into sections for readability. Every sentence contributes value, but the lack of formatting (bullets or headings) makes it harder to parse. It is front-loaded with purpose but quickly dives into details without visual separation.

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 params, 15 actions, no output schema), the description is remarkably complete. It covers the core flow (search→describe→invoke), handling of credentials and payments, tool lifecycle (install vs. invoke), permission requirements, the prompt library, and even the difference between permanent and one-off usage. Essentially every aspect is addressed.

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?

Although schema coverage is 0%, the description compensates by explaining the purpose of many parameters (action, query, mcp_id, tool_id, arguments, etc.) in context. It clarifies the meaning of 'install', 'invoke', 'list_tools', and the prompt-related actions. However, not all 23 parameters are explicitly documented, and the description doesn't systematically map each parameter to its use, leaving some gaps.

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 is 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It uses a specific verb-resource pairing and differentiates itself from siblings by outlining its unique capabilities like search/describe/invoke and the prompt library, making its 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?

It provides explicit guidance on when to use 'invoke' vs 'install', distinguishes 'list_tools', and explains the role of 'subscribe'/'cancel' and 'request_mcp'. The description effectively answers 'when to use this tool against alternatives' by detailing the core flow and stating when to prefer one action over another (e.g., 'prefer invoke for a single/occasional use').

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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is safe and idempotent. The description complements this by adding key behavioral details: the portal is hosted by the platform, requires prepaid credit per query, no platform credentials are needed, and the client is the data controller under LGPD. These disclosures go beyond the annotations and are valuable for an agent to understand the operational 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 a single, dense paragraph that front-loads the core purpose and key operational details. Each sentence adds important information: official source, platform hosting, payment model, data type, and LGPD compliance. It is concise with no filler, achieving high information density in limited space.

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 (one parameter, no output schema) and thorough annotations (read-only, idempotent, non-destructive), the description provides enough context: it covers majority of relevant aspects—data source, payment, credential requirement, data type, and legal responsibility. It doesn't describe return values, but the output schema is absent and the tool likely returns standard query results, so the description is reasonably complete for the tool's complexity.

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 one required parameter, 'cnpj', which is a string. The description does not mention this parameter at all, and schema description coverage is 0%. However, the parameter is self-explanatory: a CNPJ (Brazilian company registration number). The description could have added context about format or validation, but the name 'cnpj' is quite clear. Given only one parameter and high clarity of name, a baseline score of 3 is appropriate as the description adds minimal value over 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 purpose: consulting leniency agreements (Acordos de Leniência) from the official transparency portal. It identifies the resource (leniency agreements) and the action (consult/consultar). It distinguishes from siblings by specifying the Brazilian official transparency portal and the type of data (not secret/sigiloso), though it does not explicitly compare to other portal 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 clear context on when to use this tool: to query information from official Brazilian sources, similar to what citizens can access. It implies that it's for legitimate compliance purposes under LGPD. However, it does not explicitly state when NOT to use it or mention alternative tools by name, though the sibling list includes 'marketplace' and 'connect' which might be 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, so the safety profile is covered. The description adds a behavioral expectation (including the conversation array for reproduction), which is useful context beyond the annotations. However, it does not disclose other traits like side effects or response handling.

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 extremely concise—two sentences, no redundancy, and front-loaded with the core purpose. 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 simple tool with only three parameters and no output schema, the description covers the core purpose and provides a key hint about the conversation parameter. However, it leaves unclear semantics for message and context, and does not describe the return value or any edge cases. It is minimally adequate but not comprehensive.

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% for parameters. The description only mentions the 'conversation' parameter and its intended use (reproduction), but does not explain the 'message' (required) or 'context' parameters. This is insufficient given the high burden on the description when schema coverage is low.

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 sends feedback, using specific verbs and resources. It distinguishes itself from siblings like authenticate or 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 this tool (for reporting issues/feedback) and provides a specific guideline to include the conversation array for reproduction. It does not explicitly mention alternatives or exclusions, but given the sibling tools are unrelated, the usage 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description need not repeat those traits. The description adds the specific scope (platform and adapter versions) but does not disclose any additional behavioral traits beyond what annotations already cover.

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 that front-loads the verb and resource. Every word contributes to the meaning, with 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 simple, parameterless version-inspection tool with strong annotations, the description is fully complete. It clarifies what is returned (platform and adapter versions), and no additional context is necessary given the tool's trivial nature.

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 accepts zero parameters, so the baseline is 4. The description correctly implies no parameters are needed and adds no unnecessary parameter details, which is appropriate for a parameterless tool.

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 a clear resource ('current MCP platform and adapter versions'), making its purpose unmistakable. It distinguishes itself from sibling tools like authenticate, connect, and report_bug, and even from toolkit_info by focusing specifically on 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?

No explicit guidance is given about when to use this tool versus alternatives. While the description's core purpose is clear, it does not mention when to prefer it over similar informational tools like toolkit_info, nor does it state any exclusions or prerequisites.

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 specific return contents but no additional behavioral traits such as live vs cached data, rate limits, or dependencies, which is acceptable given annotations but does not go beyond them.

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 the current toolkit state') and efficiently enumerates the specific components. 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 status tool with no output schema, the description provides clear and relevant return-value context by listing the four key components. It is complete enough for an agent to understand what to expect, though it could mention format or whether the status is real-time.

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 coverage is 100% and there is nothing for the description to explain. The baseline for no parameters is 4, and the description does not need to compensate for missing parameter information.

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 ('current toolkit state'). It enumerates the exact contents (installed MCPs, connection status, accounts, tool counts), which distinguishes it from 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?

The description implies when to use the tool (whenever you need the toolkit state) but provides no explicit guidance about when not to use it or references any alternatives. There is no mention of exclusions or competing tools.

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