Portal da Transparência: Cadastro de Entidades Privadas sem Fins Lucrativos Impedidas (CEPIM)

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

Annotations (idempotentHint: true, readOnlyHint: false) are supplemented by the description: it clarifies the token is a JWT that the user pastes, that it creates a 'session-only login,' and that no args yields a link. It adds the 'permanent, non-expiring connection' context for the config path, which goes beyond the annotations and explains side effects. Misses explicit disclosure of what happens on repeated calls with the same token, but the idempotency hint covers that.

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 purpose but is somewhat rambling and informal ('log in in the browser' is awkward, 'Best:' is colloquial). At ~90 words for a single optional parameter, it over-explains in places. All sentences contribute useful info, but the structure could be tightened with clearer separation between the config flow, the session flow, and the no-arg case.

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 one optional parameter and no output schema, the description covers the essential flows: getting the link, session-based JWT login, and the config-based permanent alternative. The guidance on when to prefer config versus tool invocation adds practical completeness. Slight gap: no mention of error cases (e.g., invalid/expired token) or the exact format of the returned link, but this is adequate for the tool's simplicity.

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 coverage is 0% (no description on the token field), so the description carries the burden and does so well: it specifies token is a JWT pasted by the user in the { token: "<jwt>" } format, and that omitting it triggers a link response. The description effectively documents the single optional parameter, giving meaning beyond the bare 'string' type in the schema. Could add length/expiry details, but it's solid.

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 states a clear purpose: authenticating IDE agents to MCP.AI via browser login and token copy. It identifies the resource (MCP.AI for IDE agents) and the action (log in/copy token), distinguishing it from siblings like 'connect' or 'marketplace' by focusing specifically on the auth flow. However, it doesn't explicitly name alternatives or define what MCP.AI is, so it's a strong but not perfect 4.

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 guidance on two usage modes: permanent config via Authorization header (preferred) and session-only via tool call with token or no args. It clearly explains when to use each path, which aids the agent in deciding how to invoke it. However, it doesn't explicitly say when NOT to use this tool or name sibling alternatives like 'connect', keeping it just 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.

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

Annotations already declare readOnly, idempotent, non-destructive, so the bar is lower. The description adds concrete output scenarios (authenticated state and pending list vs connect_url for missing credentials), which goes beyond annotations and helps the agent anticipate return values.

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 'Returns', zero fluff. Every clause adds information about behavior in different conditions, 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?

With no output schema and simple complexity, the description covers the two main states (all connected vs missing credentials) and includes relevant tokens (authenticated, pending[], connect_url). This is sufficient for the tool's 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?

The tool has zero parameters, and schema coverage is trivially 100%. Per guidelines, baseline is 4 for 0-param tools. The description doesn't need to add parameter details and doesn't, so no deduction.

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 behavioral details (authenticated:true and empty pending[] vs connect_url). It differentiates from siblings like authenticate and show_version by focusing on status checking rather than actions or version 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 implies usage for checking connection status and contrasting with authenticate (which likely handles credentials). It does not explicitly state when not to use or name alternatives, but the context is clear enough for selection.

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 annotations (readOnlyHint:false, openWorldHint:true), the description reveals critical behaviors: invoke works without installation, returns connect/checkout links, and the one-off install behind invoke requires owner/admin. It also discloses that writes require elevated permissions and that installed_in_toolkit vs installed_in_workspace flags exist. 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 a single dense paragraph, but it is front-loaded with the core purpose and action flow before diving into finer points. Every sentence adds value with no redundancy; however, the lack of bullets or breaks makes it harder to parse. Given the complexity, it's efficient but could benefit from structural formatting.

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 14 actions, 23 parameters, and no output schema, the description covers all major functional areas: search/describe/invoke workflow, install vs invoke, billing (subscribe/cancel), feedback (report_bug), requests (request_mcp), and the prompt library. It also notes permission requirements and flag semantics. The only omission is return formats, but with no output schema, this is acceptable.

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 must compensate, and it does explain action values and the relationship between mcp_id, tool_id, and query in the flow. However, many parameters (immediate, tier_slug, prompt_vars, arguments, limit) are not explained at all, and format expectations for JSON string parameters are omitted. It partially compensates but leaves gaps for an agent to guess parameter formats and defaults.

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 stating what the tool is and its scope. It distinguishes itself from siblings by covering all marketplace actions (search, describe, invoke, install, etc.) and explicitly mentioning 'Covers capability requests...' making it distinct from auth/version tools. The high-level flow is 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 explicitly states when to use invoke vs install: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use.' It also provides guidance for list_tools, subscribe/cancel, report_bug, and request_mcp, including when no MCP fits. It even covers edge cases like authentication and payment links, making usage conditions crystal 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 safe read nature is known. The description adds valuable behavioral details beyond annotations: it is a paid operation requiring prepaid credit, does not use platform credentials, and the client is the data controller under LGPD. This informs the agent about cost and legal responsibilities, which is useful context not captured in the 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 run-on paragraph that mixes the tool's purpose with payment details, data sensitivity, and LGPD compliance. It is not front-loaded efficiently; the core purpose is stated but immediately followed by tangential legal and payment information. Several sentences could be condensed or moved to additional metadata. It lacks the crispness of a well-structured tool description.

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 query with a single parameter, the description is incomplete. It does not explain the expected format of the CNPJ, what the response contains (e.g., entity name, status, dates), or any error conditions such as invalid CNPJ or insufficient credit. It touches on payment and LGPD but omits practical usage details. Given there is no output schema, the description should have provided more on return values and edge cases.

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 one required parameter, 'cnpj', defined only as a string. The description does not explain the parameter at all: no mention that it is a Brazilian company registration number, no format guidance (e.g., digits only, with or without punctuation), no example. With schema description coverage at 0%, the description fails to compensate, leaving the agent without essential guidance for correctly providing the CNPJ.

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 it is a query to the Transparency Portal's CEPIM registry, an official Brazilian source for non-profit entities impeded from receiving public funds. While the verb 'consultar' and the resource are specific, it could be more explicit about exactly what information is returned (e.g., entity status details). It does distinguish itself from the generic sibling tools (authenticate, connect, etc.) as a data lookup.

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 usage context: it is hosted by the platform, requires no platform credentials, and is a paid query using prepaid credit. It also notes the data is not confidential and that LGPD compliance is the customer's responsibility. However, it does not explicitly state when to use this tool versus alternatives (e.g., when needing to check the impediment status of a specific CNPJ), nor does it specify when not to use it. The guidance is implied but not direct.

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 is not read-only, not destructive, and idempotent. The description adds a useful behavioral requirement to include the conversation array for reproduction, but it does not disclose what happens after submission or the response format. 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?

Two short sentences front-load the purpose and provide a concrete usage hint. Every word earns its place and there is 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?

This is a simple tool with no output schema and only three parameters. The description sufficiently covers the tool's purpose and the key conversation parameter; the only gap is the undocumented context parameter, which is optional and has a default value.

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 explicitly explains the conversation parameter (recent messages for reproduction) and implies that message contains the bug/feedback text, but it leaves the context parameter completely unexplained.

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 feedback, using the specific verb 'Report' and describing the resource types. It is clearly distinct from sibling tools like authenticate, connect, and marketplace, which are unrelated operations.

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 this tool: for bug reports, feature requests, or feedback. It doesn't explicitly mention when not to use it, but all sibling tools are obviously different in purpose, so the usage context is sufficiently 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 safety profile is well-covered. The description adds minimal behavioral context beyond what annotations provide, but it does specify the exact information returned (platform and adapter versions), which is useful. 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 that fully conveys the tool's purpose. It is front-loaded with the verb and resource, and there is zero waste. Perfectly sized for a simple, parameterless tool.

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 parameters, no output schema, clear annotations), the description is complete. It tells the agent exactly what the tool does and what information it will receive. The lack of an output schema is not a gap because the description explicitly states the content (platform and adapter versions).

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 schema description coverage is 100% (vacuously). The description adds no parameter information because none exist. Baseline for 0 params is 4, and the description appropriately focuses on the output 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's purpose: showing current MCP platform and adapter versions. It uses a specific verb ('Show') and resource ('MCP platform and adapter versions'), which is clear and distinguishes it from sibling tools like 'toolkit_info' which likely provides broader 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 implies usage context (when you need version info) but does not explicitly state when to use this tool versus alternatives like 'toolkit_info'. It lacks explicit exclusions or alternative recommendations, but the purpose is clear enough that an agent can infer appropriate 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering safety behavior. The description adds what information is returned but does not disclose other behavioral traits such as potential rate limits or caching. Given robust annotations, this is adequate but not exceptional.

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 sentence that is immediately informative, naming the exact resource and the key data points returned. No fluff, perfectly front-loaded.

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 no parameters, no output schema, and strong annotations, the description fully captures what the tool does and what it returns. It is complete for a simple informational 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, and the schema is empty with 100% coverage by default. Per rubric, a zero-parameter tool earns a baseline of 4. The description adds no parameter details because none exist.

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 with specific components: installed MCPs, connection status, connected accounts, and catalog tool counts. This verb-object structure is specific and distinguishes it from siblings like authenticate or connect that perform actions rather than provide status.

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 use for checking toolkit state, which is distinct from sibling tools that handle authentication, connection, marketplace, etc. However, it does not explicitly state when not to use it or mention alternatives, leaving usage context implicit rather than explicit.

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