Portal da Transparência: Benefício de Prestação Continuada - BPC

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

The description discloses meaningful behavioral context beyond the annotations: login happens through the browser, config-based tokens yield a permanent non-expiring connection, and pasted tokens are session-only. The annotations already indicate idempotency and non-destructiveness, and the description adds state-persistence details without contradicting 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 three sentences with the purpose front-loaded, followed by clear 'Best' and 'Or' alternatives. It is slightly verbose but every sentence adds relevant operational detail, and there is no fluff or repetition of schema fields.

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?

There is no output schema, but the description covers the main flows: obtaining a login link, pasting a token, and the recommended config-header approach. It does not specify exact response format or error handling, but for an authentication tool the described behavior is largely complete and actionable.

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 has zero description coverage, but the description compensates by explaining that 'token' is an access token/JWT pasted by the user and that calling without arguments returns the login link. This gives the agent enough semantic understanding of the single optional parameter.

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 an authentication/login mechanism for the MCP.AI server, specifically tailored for IDE agents like Cursor. It states the core actions: browser login, copy access token, get a link or supply a token. It is distinct from the sibling tools, though it does not explicitly contrast with '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 provides explicit usage paths: the best approach is adding the token to the server config as an Authorization header for a permanent connection, while pasting it provides session-only login. It also clarifies when to call with no args versus with a token. It does not discuss when to use sibling tools instead, but within this tool's scope the guidance is strong.

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 and idempotentHint. The description adds concrete output behavior (authenticated:true, empty pending[], connect_url), 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 core purpose, zero redundancy. Each sentence provides distinct value: the first states the general function, the second details conditional outputs.

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 no-parameter tool with no output schema, the description covers both possible cases (all connected vs missing credentials) and mentions the returned URLs. This is sufficient for an agent to understand and invoke 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?

Tool has zero parameters, so schema coverage is 100% by definition. Baseline for no parameters is 4; description correctly focuses on output behavior rather than params.

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 connected vs missing credentials. This distinguishes it from sibling tools like authenticate (for initiating auth) and toolkit_info (for general 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 explains the two output states (connected vs missing credentials) but does not explicitly state when to prefer this tool over alternatives. It implies usage for checking connection status, but lacks direct guidance on when not to use it or 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?

Adds rich behavioral context beyond annotations: invoke works even when the MCP is not installed, returns connect/checkout links and requires retry, writes need owner/admin, and search/describe flag installed status. No contradiction with the annotations; the description substantially expands on the safety and side-effect profile.

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 front-loaded with the core purpose and workflow, and every sentence adds operational value. It is long but justified for a 14-action gateway; the single dense paragraph slightly hurts scannability, but no content feels wasted.

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?

Covers discovery, one-off vs permanent execution, auth requirements, billing links, bug reporting, MCP requests, and the prompt library. Missing explicit response shapes for search/invoke/list_tools and semantics for resume/immediate, but overall it is quite complete for a complex tool with no output schema.

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 and 23 parameters, the description compensates well by explaining the action enum, tool_id selection, prompt variables, and auth/billing implications. However, many parameters (limit, immediate, tier_slug, cancel_reason, prompt_targets, etc.) are not explicitly described, leaving some inference burden on the agent.

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 marketplace catalog and execution layer, with specific actions (search, describe, invoke, install, publish_prompt) and a defined scope. It distinguishes itself from sibling tools by framing itself as the in-platform catalog/runner, even if the report_bug action overlaps with a sibling name.

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 guidance: search→describe→invoke as the core flow, invoke for one-off use without installation, install for permanent toolkit additions, and request_mcp when nothing fits. It also contrasts prompt-library actions and notes owner/admin requirements for writes, giving clear when-to-use direction.

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, idempotentHint, and destructiveHint=false, and the description adds meaningful context beyond that: no platform credentials, prepaid per-query pricing, official Brazilian sources, non-confidential data, and LGPD controller responsibilities. There is no contradiction with 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 front-loaded with the core purpose and each sentence contributes useful information about source, pricing, credentials, and legal context. It is slightly dense but not wasteful, and it avoids repeating the tool name or schema fields.

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 paid query tool with no output schema, the description covers official source, payment model, and data governance, but it omits the CPF input format and the shape/contents of the expected return value. The agent could select the tool confidently but would still lack some details needed to invoke 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 schema has only one parameter, cpf, with no description and schema coverage of 0%. The tool description never mentions CPF format, validation, masking, or how the value should be provided (e.g., 11 digits, with or without punctuation). A simple parameter, but the description still needs to compensate for the missing schema coverage and does not.

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 a query for the BPC benefit from the official Brazilian Transparency Portal ('consulta em fonte oficial'). It is specific about the resource, and the sibling tools (authenticate, connect, marketplace, report_bug, etc.) are clearly unrelated, so it is well differentiated.

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 practical usage context: the tool does not require platform credentials, charges prepaid credit per query, and should be used for official public BPC data under a legitimate LGPD purpose. It does not explicitly state when not to use it or name alternatives, but the sibling set makes those alternatives obvious.

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 does not contradict the annotations (idempotentHint true, destructiveHint false, readOnlyHint false). It adds no extra behavioral details beyond the annotations, but the annotations already cover side effects, so a baseline score is appropriate.

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, directly relevant, and contains no irrelevant information. It is efficiently worded without sacrificing clarity.

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 is adequate for a simple reporting tool: it states the purpose and a key usage detail. It does not describe output or post-conditions, but these are not required given the simplicity of the tool and lack of an output schema.

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 description explains only the 'conversation' parameter ('Include the conversation array'), but leaves 'context' and 'message' undocumented. Since the schema has no descriptions, the description partially compensates but not fully.

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's purpose: 'Report a bug, missing feature, or send feedback.' This is a specific verb-resource combination and distinguishes it from siblings like authenticate, connect, 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?

Provides guidance on when to use it (reporting bugs/feedback) and includes a specific instruction: 'Include the conversation array with recent messages for reproduction.' However, it does not explicitly mention alternatives or situations where this tool should not be used.

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, and non-destructive behavior. The description adds no further behavioral context beyond the annotations, such as potential side effects or performance implications, so it does not exceed the baseline established by 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 a single, clear, and concise sentence. It is well-structured with no redundancy or unnecessary detail, making it highly 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 tool that simply reports version information, the description is fully complete. It states what the tool does, and since there is no output schema or complex parameters, no additional context is necessary.

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 no parameters, and schema coverage is 100% (vacuously). Since there are no parameters to explain, the description adds no parameter-specific meaning, and the baseline score of 3 is appropriate.

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: showing current MCP platform and adapter versions. It is specific and distinct from sibling tools like authenticate, connect, and 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 implies the tool should be used when version information is needed, but it does not explicitly state alternatives or mention any use-case exclusions. The context is clear enough for a simple tool, though a more explicit 'when to use' would improve 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 the tool as read-only, idempotent, and non-destructive, covering the safety profile. The description adds value by specifying what data is returned (MCPs, connection status, accounts, catalog counts), providing behavioral insight beyond the annotations without contradicting 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, compact sentence that efficiently conveys all relevant information about the tool's output. No redundant or vague phrasing; every element listed serves a purpose.

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 tool with no output schema, the description fully specifies what the agent can expect: installed MCPs, their connection status, connected accounts per MCP, and catalog tool counts. This is sufficient for an agent to determine when and how to use 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?

With zero parameters, the schema has complete coverage trivially. The baseline for 0 params is 4, and the description doesn't need to add parameter semantics since none exist. It accurately reflects that no inputs are required.

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: it returns the current toolkit state, enumerating specific details (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from sibling action-oriented tools like connect or authenticate, making its role 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 provides clear context for when to use it (to inspect overall toolkit state) but does not explicitly mention alternatives or exclusions. Since it's a read-only info tool and siblings are action-oriented, the intended usage is evident, but there's no explicit 'when not to use' guidance.

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