IEPTB (CENPROT): Protestos

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

The description explains the login process (browser interaction) and that no args yields a link. However, it doesn't detail potential side effects (e.g., session creation, token revocation) beyond what annotations partially cover (readOnly false, destructive false). The idempotentHint is not fully elaborated.

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 but packed with relevant details, covering two usage modes without redundancy. It is slightly long but each sentence contributes to the overall understanding.

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 implies that calling with no args returns a login link, but it does not explicitly state the return value after authentication (e.g., success message or token). It also lacks error handling or edge-case information. Given no output schema, this is a notable gap.

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 single 'token' parameter is explained as optional, with the behavior for both providing and omitting it described. While the description lacks formal constraints, it adequately covers the parameter's role and options.

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 distinguishes between permanent (config header) and session-based (token) methods, making the tool's function explicit and actionable.

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 concrete usage steps: either adding the token to the config for permanent access or passing it as a parameter for session login. It implies when each approach is appropriate, though it doesn't explicitly compare with sibling tools.

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 cover read-only and idempotent behavior. The description adds value by detailing two output scenarios (all connected vs. missing credentials), including the authenticate flag, pending array, and connect URLs, which goes beyond the structured hints.

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 cover the core behavior and conditional output. No redundant phrases; 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 read-only status tool with no parameterston and no output schema, the description covers the main return states (connected vs missing credentials) and the URLs returned. It doesn't detail the shape of pending or URL structures, but with annotations and zero params, this is adequate.

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 baseline is 4. The description correctly omits parameter explanation since there are none. It adds nothing needed beyond schema, but that's fine.

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. It distinguishes from sibling tools like 'authenticate' by focusing on status rather than the authentication action itself.

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 context is implied (check connection status) but no explicit when-to-use vs alternatives or exclusions. The description explains output variations but doesn't direct the agent on when to prefer this over siblings.

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, destructiveHint=false. The description goes beyond these by explaining the commercial model (prepaid credit per query), the hosting arrangement, the non-confidential nature of the data, and LGPD responsibilities for the client as data controller. It also hints at authentication needs (login credentials or PKCS12 cert) without contradicting annotations. This enriches the behavioral profile significantly.

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 block of text that front-loads the core purpose ('Protestos, consulta em fonte oficial') then adds context on payment, data source, and legal responsibility. It is somewhat verbose (four clauses) but every sentence adds value, mixing technical, commercial, and compliance details. No wasted words, though it could be tightened by removing redundant emphasis on 'fonte oficial'.

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 6 parameters, no required fields, no output schema, and no enumeration, the description needs to fill gaps about invocation. It provides high-level context (paid, official, LGPD) but omits critical operational details: how to choose between cpf and cnpj, how authentication works (login vs PKCS12, are they alternatives?), and what the response structure looks like. It is not minimal but leaves the agent guessing on usage mechanics, so it's incomplete for a tool of this 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 6 parameters with zero description coverage. The description mentions the tool queries official sources but does not explicitly map parameters like cpf/cnpj as query identifiers or login_cpf/login_senha and pkcs12_cert/pkcs12_pass as authentication methods. It leaves the agent to infer that cpf/cnpj are probably the search keys, but gives no guidance on which are required or how they interact. The description fails to compensate 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: querying protest records (Protestos) from the official IEPTB/CENPROT source. It specifies the resource (protest records) and action (consultar), and distinguishes it from sibling tools which focus on authentication, marketplace, etc. The verb 'consultar' combined with the domain 'IEPTB (CENPROT)' leaves no ambiguity about the operation.

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: it mentions the tool is hosted on the platform, requires prepaid credits per query, does not use platform credentials, and queries official Brazilian sources with the same data available to citizens. It doesn't explicitly state when not to use the tool or name alternatives, but given the siblings are unrelated, this is adequate. It implies this is for legitimate citizen-accessible data queries.

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 significant non-obvious behavior beyond annotations: invoke works even for uninstalled MCPs as a one-off without bloating the tool list, returns a connect link when credentials are needed, returns a checkout/top-up link when payment is required, and notes that writes require workspace owner/admin. This substantially exceeds what the annotations provide and does not contradict 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 dense single paragraph but is front-loaded with the purpose and core flow. Every sentence adds information, and the length is justified by 14 actions plus the prompt library. It could be cleaner with bulleted structure, but the current flow is logical and 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?

For a complex 23-parameter, 14-action dispatcher with no output schema, the description is unusually complete: it covers the main search→describe→invoke workflow, auth/payment fallbacks, workspace permissions, and the prompt-library flow. It does not explicitly describe the return shape of search or list_tools, but it covers the most decision-critical behavior.

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 does explain the key action values and flow-level parameters (e.g., describe returns profiles so you pick tool_id, invoke runs that tool, get_prompt fills {{variables}}). However, several parameters like immediate, tier_slug, conversation, and limit are left unexplained, and there is no explicit parameter-to-action mapping.

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 scope: 'official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It clearly states the tool's role and lists the main capability groups. However, it bundles the MCP marketplace, execution runner, and prompt library into one broad purpose without explicitly differentiating from sibling tools like report_bug or 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 gives an explicit core flow: search discovers MCPs → describe returns full profile → invoke runs the tool. It also prescribes when to prefer invoke over install ('prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT'), and clarifies the roles of subscribe/cancel, report_bug, request_mcp, and the prompt-library actions.

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 non-read-only behavior. The description adds value by instructing users to include the conversation array for reproduction, which is useful context. 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?

Two sentences, front-loaded with purpose, and the additional instruction is concise. 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?

The tool is simple, but the description does not cover all parameters or explain the return behavior. It is adequate for a basic reporting tool but lacks full clarity on all inputs.

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 mentions the conversation array but does not explain the required 'message' parameter or the optional 'context' parameter. Only one of three parameters is addressed, leaving 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?

Description clearly states it reports a bug, missing feature, or feedback, using a specific verb and object. It is distinct from sibling tools like authenticate or marketplace, 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?

The description explicitly states when to use the tool (to report bugs/feedback) but does not mention exclusions or alternatives. It is clear enough for the intended use case.

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 do heavy lifting, declaring readOnlyHint: true and destructiveHint: false, which signals a safe operation. The description adds context by specifying the scope of the version info (MCP platform and adapter), indicating you get a lookup for both 'platform' and 'adapter' versions, which goes slightly beyond simple annotations. However, there's no detail on the return format or output structure. This adds value by confirming the version scope is explicitly limited to platform and adapter, which is slightly more specific than the annotations alone.

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 gets straight to the point, with no filler or extraneous detail. It's exactly as concise as it needs to be for a zero-parameter command.

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 that this is a simple, zero-parameter, read-only command with strong sibling context, the description is mostly adequate. However, it doesn't go beyond what the tool name already implies, missing the opportunity to clarify whether this is a lightweight check (no server connection) or if it adds value like connecting to the server, which would be useful for context. It leaves the return format ambiguous but is otherwise fit for purpose.

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?

This is a tool with zero parameters, meaning there's no parameter documentation to add or look up. The schema is empty, and since the description doesn't need to explain any inputs, the baseline of 3 serves as the starting point. The description adequately covers the tool's purpose without needing to reference parameters, and there's nothing in the schema that remains undocumented.

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?

'Show the current MCP platform and adapter versions' uses a specific verb ('show') and identifies the exact resource ('MCP platform and adapter versions'). This clearly defines the tool's purpose and differentiates it from siblings like 'authenticate' or 'connect'. The term 'current' also correctly implies read-only access to running state, leaving no ambiguity about what the command does.

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?

For a read-only informational tool, the implicit usage is clear: invoke this to ascertain version details. However, the description provides no explicit guidance on when one might use this versus tools like 'toolkit_info' or whether it's used for debugging/reporting. Unlike the 'authenticate' or 'connect' siblings, there's no mention that no connection is needed, but the tool is simple enough that this gap is minor.

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 value by revealing the precise contents of the toolkit state (connections, accounts, tool counts), going beyond the generic annotation information.

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 primary purpose and lists details in a compact, readable manner. Every word contributes to the meaning, with 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 read-only info tool with no parameters and no output schema, the description provides enough detail to understand what the tool returns. It does not specify the exact response format, but that would be redundant for the selection and invocation task.

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 there is nothing to explain. The baseline of 4 applies, and the description correctly focuses on the return value rather than parameters.

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 the specific contents: installed MCPs, connection status, connected accounts, and catalog tool counts. This distinguishes it from sibling tools like connect or 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 implies usage when the agent needs to inspect the toolkit state. It does not explicitly exclude alternatives, but the read-only scope and detailed content make appropriate use clear without confusion with sibling tools.

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