Antecedentes Criminais: MG

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

The annotations already indicate read-only and idempotent. The description adds valuable context: the data comes from official Brazilian sources (not confidential), the payment model (prepaid credit), and LGPD responsibilities. This goes beyond the boolean 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 about four sentences, front-loading the main purpose. While the legal and payment disclaimers add length, they are relevant and the text remains scannable.

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 lookup tool with two string parameters and no output schema, the description covers the core purpose and legal aspects. However, the complete lack of parameter guidance means an agent may not reliably format a valid request.

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 provides zero information about the 'rg' or 'cpf' parameters. With schema description coverage at 0%, the agent gets no hints about formats, which identifier to use, or whether either is required. This is a critical omission.

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 immediately begins with 'Antecedentes Criminais: MG, consulta em fonte oficial,' specifying the action (query) and resource (criminal background in Minas Gerais). This clearly differentiates it from generic sibling tools like 'authenticate' and '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 context about the service—official source, prepaid credit, no platform credentials—but does not explicitly state when to use this tool versus alternatives or any prerequisites. The use case is implied rather than spelled out.

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 include idempotentHint=true and destructiveHint=false, and the description adds valuable context: it explains that a config header gives a permanent, non-expiring connection while a pasted token is session-only. It also implies that calling with no args returns a link for browser login, disclosing the primary interaction flow. 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 compact (three sentences), front-loaded with the primary purpose, and structured logically: first stating the tool's role, then presenting the two usage modes (config vs token), and finally the call variants. Every sentence adds essential information without 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?

Given the tool's simplicity (one optional parameter, no output schema) and the informative annotations, the description is complete. It explains all usage scenarios, the token handling, and the distinction between permanent and session authentication, leaving no significant gaps for an agent to misunderstand.

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 one token parameter with no description coverage, but the description fully explains its meaning: a JWT to paste for session login. It also clarifies that omitting the token returns a login link, effectively describing the parameter's purpose and the no-argument behavior. This fully compensates for the schema 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 authenticates the user for MCP.AI in IDE agents, with specific actions: logging in via browser, copying token, and using token for session login or no args for link. It distinguishes from siblings by focusing solely on authentication, which is unique among the listed tools.

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 explains when to use this tool (login for IDE agents) and how: either add token to config for permanent connection or paste token for session-only login, or call with no args to get a link. It also contrasts the two methods, providing clear alternatives and conditions for each, which is excellent 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 readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds behavioral context by explaining the return value structure and the conditions that trigger different outputs (authenticated:true with empty pending[], or connect_url with per-install URLs). This goes 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 two sentences, front-loaded with the primary action, and every phrase adds value. It is concise and well-structured without 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 tool with no parameters and no output schema, the description adequately explains the return values and the two main states (all connected vs missing credentials). It is complete enough for an agent to understand what to expect.

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, so the baseline is 4. The description does not need to explain parameters, and it does not miss anything in that regard.

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', which is a specific verb and resource, and it distinguishes itself from sibling tools like 'authenticate' by focusing on status rather than performing authentication. The conditional outputs (authenticated:true vs connect_url) add further clarity.

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 about when the tool is useful by explaining the conditions under which different results are returned (all providers connected vs credentials missing). It does not explicitly name alternatives or state when not to use it, but the context implicitly differentiates it from siblings like 'authenticate'.

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 critical behaviors beyond annotations: invoke works even for uninstalled MCPs (one-off), returns connect links for missing credentials and checkout links for empty wallets, requires owner/admin for writes, and flags installed status in search/describe. It does not contradict any annotations (readOnlyHint=false, openWorldHint=true, etc.) and adds substantial context.

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 necessary for a tool with 14 distinct actions. It is well-structured: begins with the top-level purpose, then explains the core flow, then details invoke/install trade-offs, and finally covers the prompt library. Every sentence adds value; no waste. Slightly padded with repetitive phrasing (e.g., 'pontualmente' and 'one-off' both used), but overall appropriately sized.

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 complexity (23 params, 14 actions, no output schema), the description is remarkably complete. It explains return behaviors (connects links, checkout links, flags), permissions, and alternative tools. It does not spec exact return formats for each action, but without an output schema that would be expected; moreover, it gives enough to guide an agent on what to expect. Nearly perfect for a handbook-style 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?

Although schema_description_coverage is 0%, the description explains the action parameter thoroughly (each enum value's purpose) and implies the roles of mcp_id, tool_id, arguments, and prompt_* parameters through the flow descriptions. It does not individually define every one of the 23 parameters, but given the tool's nature as a dispatcher, the action semantics are the core, and those are well covered. A slight deduction for not explicitly tying other parameters to their meanings.

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 this is the mcp.ai marketplace, a catalog and execution engine for all MCP/tools. It explains the core flow (search → describe → invoke) and distinguishes itself from sibling tools like antecedentes_criminais_mg_consultar, authenticate, connect, report_bug, show_version, and toolkit_info. It even covers a secondary function (prompt library), making the purpose unambiguous and complete.

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 on when to use each action: invoke for one-off usage, install for permanent addition, list_tools for current callables, request_mcp when nothing fits. It also contrasts invoke vs install with reasons, and explains when to use the prompt library sub-actions. This is model clarity.

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 not read-only and not destructive; the description adds that it sends the conversation for reproduction, giving context about data included.

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 concise sentences with no redundancy or irrelevant information.

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 simple schema and lack of output schema, the description is somewhat incomplete as it only clarifies the conversation parameter, leaving the required message parameter unexplained.

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?

Only mentions the conversation parameter but does not explain the required message or optional context. Schema coverage is low, and the description fails to compensate for the missing parameter explanations.

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?

Clearly states it reports bugs, missing features, or feedback, which distinguishes it from sibling tools like authenticate or 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?

Provides an instruction to include the conversation array for reproduction but does not explicitly state when to use this tool versus alternatives or any prerequisites.

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 false, so the safety profile is clear. The description adds that it shows platform and adapter versions, which is the core behavior. No additional behavioral nuances are necessary for this simple read-only operation.

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 sentence that gets straight to the point. There is no wasted text, and it is front-loaded with the main 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 tool with no parameters and no output schema, the description is complete. It fully explains the tool's function, and the annotations cover the behavioral aspects. There is no missing information that would hinder an agent's ability 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 tool has no parameters, so there is nothing the description needs to clarify. The description succinctly states what the tool does without needing to elaborate on parameters. A baseline of 4 is appropriate for a zero-parameter 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 action ('Show') and the resource (current MCP platform and adapter versions). It is specific and unambiguous, leaving little room for confusion with any sibling 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 implies usage for checking version information, which is a common informational task. There are no explicit exclusions or alternatives, but given the simple nature of the tool and the absence of similar sibling tools, the context is reasonably 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 covered. The description adds the specific content returned but does not mention any potential side effects or limitations (e.g., whether the state is cached or real-time). Since annotations carry the burden, this is adequate but not rich.

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, well-structured sentence that immediately states the tool's purpose and details. No wasted words, 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?

For a simple zero-parameter tool with comprehensive annotations, the description fully captures what the tool returns. The output schema is absent, but the description enumerates the key elements, making it complete for an agent's needs.

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 does not need to explain parameters, and the schema confirms none exist. No additional meaning 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 returns the current toolkit state, listing specific components (installed MCPs, connection status, accounts, catalog tool counts). This is a specific verb+resource combination and distinguishes it from siblings like show_version and 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 purpose is unambiguous and implies usage for checking overall toolkit status, but there is no explicit guidance on when to use it over sibling tools. Since it's a zero-param info tool and siblings have distinct functions, the context is clear enough; no exclusions are stated.

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