SEFAZ MG: Protesto Inscrito em Dívida Ativa

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

The description discloses the behavior of generating a login link with no arguments, as well as the distinction between permanent (config header) and session-only (pasted token) connections. It adds context beyond the annotations (idempotentHint=true) by explaining the non-expiring nature of the config approach, without contradicting any 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 functional but somewhat stream-of-consciousness, combining context, a recommendation, and usage instructions into a single run-on paragraph. It could be better structured with bullet points or separate sentences for clarity, though every sentence adds value.

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 optional parameter, no output schema), the description covers the essential flows: config-based and session-based, including the outcome of each. It omits error handling or success responses, but for an auth tool this is sufficient.

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 the schema only defines 'token' as a string, the description clearly explains its expected format (JWT) and usage via the example `{ token: '<jwt>' }` and the no-arg case. It fully compensates for the lack of schema-level descriptions, providing complete semantic meaning.

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 'MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token,' making the tool's purpose unmistakable. It uses a specific verb ('authenticate') and resource ('MCP.AI'), and is clearly distinct from sibling tools like 'connect' or 'marketplace' by focusing on authentication.

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 offers explicit usage guidance by contrasting 'Best: add it to this server's config as a header' for a permanent connection versus 'paste it here for a session-only login.' This effectively tells users when to choose each flow, though it does not explicitly mention alternative tools or when not to use them.

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 establish readOnly, idempotent, and non-destructive behavior. The description adds valuable behavioral detail beyond annotations by explaining what the response looks like in both connected and missing-credential scenarios, including the connect_url and per-install URLs. This meaningfully enriches the agent's understanding.

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 primary purpose, and every clause adds relevant information. It is compact while covering the key state-dependent 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?

Given the tool's simplicity (no parameters, no output schema), the description fully covers what an agent needs: the purpose, state-dependent response, and connection-related URLs. The annotations further cover safety and idempotency concerns, making the description contextually 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?

The tool has zero parameters, so the baseline is 4 per the rubric. The description does not need to explain parameters and correctly focuses on the behavior and return states.

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: returning connection status and URLs. It also specifies distinct response conditions (all providers connected vs. credentials missing), making its purpose unambiguous and differentiating it from sibling tools like authenticate or 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 provides clear context for when to use the tool by detailing the expected outputs under different states (authenticated vs. missing credentials). It does not explicitly name alternatives or exclusions, but the use case is evident: check connection/authentication status without performing an action.

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 substantial behavioral context beyond minimal annotations. It discloses that invoke runs one-off without installation, that install makes permanent changes, that writes require owner/admin, and that invoke may return connect or checkout links requiring user action. These are critical side effects not captured by readOnlyHint, idempotentHint, or destructiveHint, and they are clearly stated.

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 long but information-dense, front-loaded with the core purpose and flow. Each sentence adds value: it covers the main flow, the key differences between invoke and install, permission requirements, and the prompt library. While not concise in length, it is well-structured and avoids redundancy, justifying its size given the tool's complexity.

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 23 parameters, no output schema, and minimal annotations, the description covers the essential context: the action flow, return behaviors (e.g., describe returns full profile, invoke returns links), authentication/payment handling, permission requirements, and the prompt library. It orients the agent on what each action does and the expected follow-up steps, making it sufficiently complete for effective tool selection and invocation.

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 0% parameter description coverage, so the description must compensate. It thoroughly explains the action parameter by enumerating all 14 actions and their purposes, and indirectly covers mcp_id, tool_id, arguments, and prompt_* fields through the described flow. However, it does not explicitly document parameters like limit, query, message, or cancel_reason, relying on defaults/enums. Despite this gap, the description provides enough context for an agent to correctly construct most calls.

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 that marketplace is the official MCP catalog and execution platform, covering capability requests. It distinguishes from siblings by listing specific actions like search, describe, invoke, and install, which are not handled by other tools. The verb 'catalog' and 'run' plus the action list make the purpose 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 explicit usage guidance: 'prefer invoke for a single/occasional use' versus 'use install only to make an MCP PERMANENT.' It names alternatives like list_tools for currently callable tools, subscribe/cancel for billing, and request_mcp for new builds. It also explains when to search vs describe, and the retry flow after connect/checkout links.

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?

It adds a note about including conversation but does not detail side effects, permissions, or limitations. Annotations provide some flags, but the description could mention that reporting creates a record.

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, no redundant content, and it gets straight to the point.

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 and no explanation of what happens after reporting (e.g., return value, errors, or follow-up). The tool's behavior beyond the input is unspecified.

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 mentions 'conversation' but does not explain 'message' or 'context'. With zero schema coverage, it only partially compensates for the required parameter and others.

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: reporting bugs, missing features, or sending feedback, and includes an instruction for reproduction.

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 gives a concrete usage instruction (include conversation for reproduction) but does not explicitly compare with alternatives, which is acceptable given the sibling tools are unrelated.

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, establishing a safe read operation. The description adds valuable behavioral context beyond annotations: no platform credentials needed, pay-per-query with prepaid credit, data is the same as available to citizens and not confidential, plus LGPD controller responsibilities. This enriches the agent's understanding of cost and legal usage.

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 paragraph of three sentences, front-loading the primary purpose first. Each sentence adds distinct value (source, payment/auth, data nature, legal responsibility), though the LGPD clause is somewhat verbose for an AI agent. Overall, it is concise and well-ordered.

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 cost, authentication, and data classification, but it is incomplete for a query tool with 4 undocumented parameters and no output schema. It does not specify what inputs are expected (beyond the schema names), whether any combination is valid, or what the response contains. The agent cannot reliably invoke the tool without further information.

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 4 parameters (ie, cpf, pta, cnpj) with no descriptions (0% coverage). The description does not explain any of these parameters, their meaning, or how they relate to the 'protesto' query. The agent is left guessing what identifiers to provide, making this a critical gap.

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 as a query ('consulta') for 'Protesto Inscrito em Dívida Ativa' from SEFAZ MG, identifying a specific verb, resource, and official source. This distinguishes it from the general sibling tools (authenticate, marketplace, etc.).

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: the tool is a paid per-query service using prepaid credits, hosted on the platform, and querying official non-confidential data. However, it does not explicitly state when to use this tool versus potential alternatives (e.g., other SEFAZ query tools), nor does it mention exclusions or prerequisites beyond payment.

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 scope of what is being reported (MCP platform and adapter versions), which goes slightly beyond the annotations by clarifying the exact information returned. This aligns well and adds modest value beyond the structured data.

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, focused sentence that leads with the action verb 'Show' and clearly states the object. Every word serves a purpose, and the sentence is front-loaded. It is the ideal length for such a simple 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?

For a zero-parameter, read-only version tool with comprehensive annotations, the description provides all necessary context. It tells the agent exactly what information is exposed (MCP platform and adapter versions) without overcomplicating things. The lack of an output schema is not an issue here, as the tool's return value is self-evident from the description.

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 description has no parameters to explain. The baseline of 4 is appropriate since the empty input schema means there is no parameter documentation gap. The description doesn't add parameter-related semantics, but none are needed.

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') with a precise resource ('current MCP platform and adapter versions'), making its function immediately clear. It distinguishes itself from sibling tools like 'authenticate' or 'report_bug' by explicitly targeting version introspection, leaving no ambiguity about its purpose.

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 on when to use this tool versus alternatives. However, the straightforward nature of a version-checking tool makes its usage implied (e.g., when you need to know the MCP platform/adapter versions). It doesn't provide alternatives or exclusions, so it earns the 'implied usage' middle score.

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, which informs the agent that this is a safe read operation. The description adds that it returns state information, but doesn't detail edge cases like what happens if no MCPs are installed or if an account connection fails. Since annotations cover the safety profile, a 3 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 a single sentence that is concise, informative, and front-loaded with the primary purpose. No redundant words; every phrase adds value.

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 simplicity (0 params, no output schema) and the read-only nature, the description is complete enough. It lists all the key aspects of the return value. However, it could mention that the state is a snapshot or that it reflects current connections, but that's minor.

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 0 parameters, so the schema provides no parameter semantics. The description compensates by clarifying exactly what information is returned: installed MCPs, connection status, accounts, and catalog counts. This fulfills the purpose of the tool with no parameters needed.

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 describes what it returns (installed MCPs, connection status, accounts, catalog tools). It is a read-only introspection tool that queries the current state, distinguishing itself from the siblings that might have similar 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 when to use it (when you need current toolkit state) but does not explicitly state when not to use it or mention alternatives like show_version or marketplace. Given the simple nature, this is adequate but lacks explicit guidance.

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