Antecedentes (Polícia Federal)

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds context about public-access data, prepaid credit payment, no credentials, and LGPD responsibility, going beyond the structured metadata without contradicting it.

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 main action and delivers relevant operational context (payment, access level, legal responsibility) in four sentences. It is slightly dense but 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?

The description covers purpose, self-consultation scope, payment model, and data-public nature. However, with no output schema and six parameters, it leaves parameter formats and the exact response structure unspecified, which lowers completeness.

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%, and the description only mentions 'CPF e nome' as inputs, omitting the required NomeMae, NomePai, DataNascimento, and optional completo parameters. It does not compensate for the lack of parameter documentation in the 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 function with a specific verb ('Consulta') and resource ('certidão de antecedentes criminais na Polícia Federal'), and explicitly scopes it to the holder consulting their own record. This distinguishes it from the unrelated sibling 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?

It provides clear context on when to use: 'Feito para o titular consultar os próprios antecedentes' indicates self-service only. It does not explicitly list alternatives or when-not scenarios, but the restriction narrows usage sufficiently.

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 context beyond annotations by explaining the session-only nature of the token passed to the tool versus the permanent nature of the config header. It also clarifies the flow: no args returns a link, token input authenticates. This supplements the annotations (readOnlyHint=false, idempotentHint=true) with practical usage 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 about three sentences long and front-loads the essential context (MCP.AI for IDE agents) before giving instructions. Each sentence adds distinct information: obtaining the token, the permanent config option, and the session-only tool usage. No extraneous content.

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 main use cases and return behavior for the no-arg case (returns link), but does not explicitly state the return for a token call (e.g., success message). Given the simple tool and available annotations, this is a minor gap but not critical.

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 lists an optional 'token' string with no description (0% coverage). The description fully compensates by defining it as a JWT access token, explaining how to obtain it, and clarifying that omitting it returns a login link. This gives the parameter clear 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 clearly explains the tool's role in authentication, instructing the caller to either provide a JWT token via the 'token' parameter or call with no arguments to receive a login URL. It distinguishes itself from the 'connect' sibling by focusing specifically on the authentication handshake.

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 explicitly recommends adding the token to the server's config as a permanent header instead of using the tool for persistent auth, stating this is 'Best.' It then explains the tool is for session-only login when the token is pasted directly, giving clear when-to-use and when-not-to-use guidance. No alternative tools are named, but the config method is an alternative.

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, covering safety. The description adds valuable behavioral details by specifying exact return states (authenticated:true with empty pending[] vs. connect_url for toolkit and per-install URLs) that are not inferable from annotations alone.

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, immediately states the primary purpose, and then adds two concise conditional scenarios. Every word earns its place without fluff or repetition.

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 there is no output schema, the description compensates by explaining the two main return scenarios. However, it does not clarify behavior for partial provider connectivity (e.g., some connected, some missing), which could be a gap. Still, it is reasonably complete for a status 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 takes zero parameters, and the schema coverage is 100% (trivially). No parameter explanation is needed. Per rubric baseline for 0 parameters is 4.

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 ('Returns') and clearly identifies the resource ('connection status and URLs'). It distinguishes this from the sibling 'authenticate' tool by focusing on status/URL retrieval rather than authentication actions.

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 (checking connection status or obtaining connection URLs when credentials are missing), but it does not explicitly mention alternatives or when not to use. Conditional language ('When all providers are connected', 'When credentials are missing') gives practical 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?

The description goes well beyond annotations by disclosing critical behaviors: invoke works even when the MCP is not installed, returns a connect link if credentials are needed, and returns a checkout/top-up link if payment is required. It also states that writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin, and that search/describe flag installed_in_toolkit vs installed_in_workspace. These details provide rich operational context not available in 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 long but well-structured, starting with the high-level purpose and then explaining the core flow, key behaviors, permissions, and the prompt library. Every sentence delivers meaningful information, and the logical flow from search → describe → invoke → install makes it easier to follow. It is not as brief as ideal, but the complexity of 14 actions and 23 parameters justifies the length.

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 provides a strong overview of the marketplace, covering search, describe, invoke, install, uninstall, list_tools, subscribe/cancel, report_bug, request_mcp, and the prompt library. It explains important edge cases like connect links and checkout links. However, a few actions (e.g., resume) and parameters (e.g., conversation) are not addressed, leaving some gaps in an otherwise comprehensive 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?

The description adds meaning to core parameters like action, mcp_id, tool_id, and arguments through the explained flow (e.g., 'describe returns one MCP's full profile ... so you pick the right tool_id → invoke RUNS that tool'). However, with 23 parameters and 0% schema coverage, many parameters such as query, limit, prompt_* fields, cancel_reason, and request_details are not explained. The description provides a high-level flow but does not systematically cover each parameter's purpose, so it only partially compensates for the coverage 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 opens with 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' clearly stating the tool's purpose and scope. It distinguishes itself from siblings by covering the entire catalog and execution layer, not just a single function. The description also enumerates the main actions, showing it is the central marketplace and execution hub.

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 when to use which action: 'Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile ... so you pick the right tool_id → invoke RUNS that tool.' It also contrasts invoke vs install: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT in the active toolkit.' It additionally clarifies list_tools for current callable tools, subscribe/cancel for billing, and request_mcp for new MCPs, giving clear decision-making instructions.

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 a non-read-only, non-destructive, and idempotent operation. The description adds useful context by instructing to include the conversation array for reproduction. However, it does not disclose post-submission behavior or side effects, leaving some transparency gaps.

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 conveys the core purpose and a key usage hint. No filler or repetition exists.

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, the description covers the main intent and the conversation field. However, it omits the 'context' parameter and any information about expected outcomes, making it adequate but not fully comprehensive.

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. It adds meaning to the 'conversation' parameter by specifying it should contain recent messages, and implies 'message' is the report content. However, the 'context' parameter is entirely undocumented, leaving a semantic 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 uses specific verbs ('Report', 'send') and identifies the resource ('bug, missing feature, or feedback'). This makes the tool's purpose immediately clear and distinguishable from the unrelated sibling 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 implies usage for reporting issues but provides no explicit guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. The sibling tools are unrelated, but no context is given.

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 output (platform and adapter versions), which is useful, but does not disclose additional behavioral traits such as return format or potential side effects, though none are expected for a version query.

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 delivers the essential information without any superfluous detail. It is front-loaded and directly 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?

For a simple, parameterless version lookup tool with strong annotations, the description is fully complete. It explains what the tool does, and no output schema or parameter details are necessary. The sibling tools do not overlap, so no additional disambiguation is required.

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 score is 4. The description correctly implies no inputs are required, and there is no parameter information needed beyond what the empty schema already provides.

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: 'Show the current MCP platform and adapter versions.' The verb 'Show' and the specific resource (platform and adapter versions) make it unambiguous and distinct from sibling tools like authenticate or 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 conveys clear context for when to use the tool: whenever current version information is needed. It does not explicitly mention alternatives or exclusions, but given the tool's narrow purpose, the usage context is self-evident.

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, which fully covers the safety profile. The description adds meaningful contextual detail about the return payload (installed MCPs, connection status, accounts, catalog tool counts), going beyond what annotations alone provide. 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 sentence that is front-loaded with the verb and resource. Every phrase adds value, listing the specific data returned without any redundant or filler content.

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 parameterless, read-only status tool with no output schema, the description is complete. It explains both what the tool does and what data it returns, making it fully sufficient for an agent to select and 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 takes zero parameters, so the baseline is 4. The description doesn't need to explain any parameter semantics, and no further compensation 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 uses the specific verb 'Returns' and names the resource 'current toolkit state', then enumerates exactly what is included (installed MCPs, connection status, accounts, catalog tool counts). This clearly differentiates it from sibling tools like show_version or connect, which have 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 its use case—when you need the toolkit state and connection status—but does not explicitly state when to use it over alternatives or mention exclusions. The absence of parameters and the self-contained nature make the context clear enough, but it stops short of explicit guidance.

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