SEFAZ PI: Solicitar Certidão Negativa da Dívida Ativa (CNDA)

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

The description adds behavioral context beyond the annotations: it explains the permanent versus session-scoped nature of authentication and the effect of calling with or without arguments. The annotations already declare idempotent and non-destructive, and the description does not contradict them. It stops short of describing response details or side effects on existing sessions, which could justify a higher score.

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 front-loaded with the main idea. It contains no fluff, but the sentences are a bit dense and could be split for readability. The formatting with colons and semicolons is acceptable but not ideal.

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 two call modes adequately but does not specify the return format for the token call (only 'get the link' for no args). With no output schema, the agent is left guessing what a successful token authentication returns. For a moderately complex tool with two modes, 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 parameter 'token' is not described in the schema, but the description fully compensates by explaining it as a JWT and showing how to use it ('call with { token: "<jwt>" }'). It also clarifies that calling with no args returns the link. This adds significant meaning beyond the bare 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 tool's purpose: to authenticate by either providing a login link or accepting a token. It uses specific verbs like 'log in' and 'call with' and explains the two modes. However, it does not explicitly distinguish itself from sibling tools such as 'connect', so it misses the explicit differentiation that would earn a 5.

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 clear usage context: it explains the recommended permanent setup via config header and the session-only alternative via pasting a token. It also instructs how to get the login link. It does not explicitly mention when not to use the tool or name alternatives, so it lacks the exclusions needed for 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?

The description adds conditional behavioral detail beyond the readOnlyHint/idempotentHint annotations, explaining that authenticated:true and empty pending[] appear when connected, and connect_url appears when credentials are missing. This is genuinely useful context for an agent deciding how to interpret results.

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 and front-loads the primary purpose. It wastes no words and packs meaningful conditional output detail into a compact 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?

For a no-argument, read-only status tool, the description covers the main return scenarios: authenticated with empty pending, and missing-credential state with toolkit/per-install URLs. It does not specify the full response shape, but no output schema exists and the tool is simple enough that the description provides adequate context.

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 parameter semantics are not a concern. The description is clear that the tool takes no input and simply returns status, which is sufficient.

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 explicitly says the tool returns connection status and URLs, which clearly identifies its function. It distinguishes itself from sibling tools like authenticate by being a read-only status check rather than an action that establishes a connection.

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 clear conditional context for when to use the tool: to check whether all providers are connected or to see what connect URLs are available when credentials are missing. It does not explicitly say 'use this instead of authenticate', but the read-only status framing makes that implied.

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 goes well beyond the annotations by disclosing that writes require workspace owner/admin, that invoke can run an MCP without installing it, and that credential or payment gaps produce connection/checkout links. Since annotations already say the tool is not read-only, the extra behavioral details add clear value, although response shaping and pagination are not addressed.

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 packs a great deal of important information into one long, dense paragraph with little visual structure. It front-loads the main identifiebut but the sentence that mix core flow, exceptions, write permissions, billing, and prompt-library discussion together make it harder to parse than a bulleted or sectioned description would be.

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 very complex action-router with 14 actions and no output schema, the description is remarkably complete: it covers the core invoking flow, conditions around credentials and payments, distinguishing one-off vs permanent install, and maps the capability queries to search_prompts/get_prompt/publish_prompt. The main gap is that it does not explain the 'resume' action or the precise role of several optional params.

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 23 parameters and 0% schema description coverage, the description matters, and it does add high-level meaning by explaining the action values and the search/describe/invoke roles of mcp_id and tool_id. However, many parameters such as immediate, tier_slug, conversation, request_details, prompt_title, and prompt_description remain unexplained, so the description only partially compensates for the missing schema 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 opening sentence clearly identifies the tool as 'the official mcp.ai marketplace' and gives its dual role: catalog and execution layer. It then names the core flow of search, describe, and invoke, making the tool's purpose unmistakable and distinguishable from a generic listing or CRUD tool.

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 when-to-use guidance: it says 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use' and distinguishes list_tools, subscribe/cancel, report_bug, request_mcp, and the prompt-library actions. This gives an agent clear decision logic for the task variants.

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 safety-related traits: readOnlyHint is false, destructiveHint is false, and idempotentHint is true. The description adds the reproduction context but does not disclose what happens after a report is submitted, such as whether confirmation is returned or whether any follow-up occurs.

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 one sentence and front-loads the core purpose before giving one essential parameter guideline. No word is wasted and no modifier is repeated.

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 fairly simple, and the annotations provide safety and idempotency context. However, the description leaves important input semantics to the caller's inference, especially for the required 'message' parameter and the optional but undocumented 'context' parameter, so it is adequate but not fully complete.

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 the parameter semantics. It explains that 'conversation' should contain recent messages for reproduction, but it does not clarify the meaning of 'message' or 'context', and calling 'conversation' an array could confuse callers since the schema types it as a string.

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 specific verb 'Report' and names its exact targets: bug, missing feature, or feedback. This makes the tool's purpose immediately clear and distinguishes it from unrelated siblings like authenticate, marketplace, and show_version.

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 directly states when to use the tool: reporting a bug, missing feature, or sending feedback. It also gives a concrete usage hint by asking the caller to include the conversation array for reproduction, though it does not explicitly list any alternatives or 'when not to use' scenarios.

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?

While annotations already mark the tool as read-only and idempotent, the description adds value by disclosing payment-per-query, absence of platform credentials, LGPD compliance, and data controller responsibilities. This goes beyond structured metadata, though it could mention rate limits or response behavior.

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 then adds relevant operational and legal context (cost, LGPD, data source). It is economical with words, though breaking it into bullet points could improve scannability.

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 (2 optional parameters, no output schema). The description covers purpose, data source, and compliance, but omits how parameters should be supplied (e.g., one of CPF/CNPJ required) and what the response contains. It is adequate but not thorough.

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 two parameters (cpf and cnpj) with zero description coverage. The description does not explain what these fields are for, that at least one is required, or how they map to CPF/CNPJ. With 0% schema coverage, the description fails to compensate, leaving the agent without essential information to correctly invoke the 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 clearly states the tool's function: 'Solicitar Certidão Negativa da Dívida Ativa (CNDA), consulta em fonte oficial.' It specifies the resource (CNDA from SEFAZ PI) and the action (request/query), and distinguishes itself from generic sibling tools by naming a specific official source.

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 (e.g., it's a query to official sources, costs prepaid credit, and handles non-confidential data) but does not explicitly state when to use this tool over alternatives or provide exclusion criteria. It gives some operational details but lacks direct when-to-use 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?

Annotations already declare read-only, non-destructive, and idempotent behavior. The description adds no new behavioral details beyond what is already known. Since annotations cover the essentials, a score of 3 is appropriate as the description provides minimal additional insight.

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 with no fluff. It fully conveys the purpose in minimal words, achieving high efficiency.

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 version query, the description is complete. It specifies what information is returned (platform and adapter versions) without needing to detail return format, which is acceptable given the simplicity and lack of 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 zero parameters, the baseline is 4. The description correctly implies no inputs are needed, and the schema confirms no parameters. No additional parameter documentation is 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 shows the current MCP platform and adapter versions, which is specific and distinct from the sibling tools (authenticate, connect, marketplace, report_bug, sefaz_pi_cnda_consultar, toolkit_info). It uses a clear verb 'show' and identifies the 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 does not explicitly state when to use this tool over alternatives, but it is a simple version-check operation. The intended context (e.g., when user asks for platform or adapter versions) is implied, though no exclusions or alternatives are mentioned.

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, so safety is covered. The description adds valuable behavioral detail about what it returns: installed MCPs, connection status, accounts, and catalog tool counts. It does not contradict annotations, and provides extra context beyond the safety flags.

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 clearly conveys the tool's purpose without any filler or redundancy. It is front-loaded with the verb and subject, making it efficient for an agent to parse.

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 there are no parameters and no output schema, the description sufficiently captures what the tool returns, including the core information categories. It is complete for its intended simple informational role and requires no additional clarifications.

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?

There are no parameters, so schema coverage is trivially 100%. Per the rubric, a 0-parameter tool gets a baseline of 4. The description does not need to explain anything about parameters, as 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 explicitly states that it returns the current toolkit state, including installed MCPs, connection status, connected accounts, and catalog tool counts. The verb 'returns' and the resource 'toolkit state' make it clear, and it is distinct from sibling action 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 does not explicitly state when to use this tool versus alternatives or provide exclusions. Its purpose as a status/state query is implied, but without explicit guidance, the agent must infer usage context. A clear 'use for checking state' hint would improve it.

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