Secretaria de Inspeção do Trabalho: Trabalho Escravo

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

Annotations declare idempotentHint=true and destructiveHint=false, and the description does not contradict them. The description adds behavioral context by explaining that calling with no args returns a login link, and that providing a token enables session-only login. However, it doesn't state that the token might be validated or what errors might occur, so it adds some but not extensive transparency beyond 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 concise, with three sentences that each serve a purpose: explaining the purpose, recommending permanent config, and explaining invocation patterns. It is fairly front-loaded, stating the tool's function immediately. Slightly verbose due to the multiple alternatives, but still tight.

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 tool with one optional parameter and no output schema, the description covers the key scenarios (no args, token arg) and provides necessary guidance. It does not mention return values, but without an output schema, the agent might need to infer that the tool returns a link or success message, which is a minor 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 schema has only one parameter (token) with 0% schema description coverage. The description does explain the token parameter's meaning (a JWT token to paste for session login), which adds value beyond the schema's bare property definition. However, because there is essentially one parameter and the description covers it well, the score is at baseline.

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 the user by logging in via browser, obtaining a token, and optionally storing it for permanent or session-only access. It distinguishes this from sibling tools (e.g., connect) by highlighting its focus on authentication, though it doesn't explicitly contrast with 'connect', but the function is distinct.

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 when-to-use scenarios: call with no args to get the link, call with token after user has pasted it, and recommends adding the token to config for permanent connection. It effectively tells the agent how to handle different authentication states, which is a strong usage guideline.

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 covered. The description adds value by detailing the return behavior under two conditions (all providers connected vs missing credentials), which goes beyond the static annotations. No contradictions detected.

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 at two sentences, both front-loaded with the core function (returning status and URLs) followed by conditional details. Every sentence adds essential information, with no filler or 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 tool with no parameters and no output schema, the description fully explains what the tool returns and under what conditions. The annotations cover safety, and the two behavioral cases are clearly described. This is complete 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?

The tool has zero parameters, so the description has no need to explain parameters. Per the rubric, baseline for 0 params is 4. The description does not add parameter-specific information, but that is not necessary here. It appropriately focuses on output behavior.

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 behavior for connected vs missing-credential scenarios. This distinguishes it from siblings like 'authenticate' which handles authentication, and 'marketplace' which deals with marketplace functions. The verb 'Returns' plus resource 'connection status and URLs' is specific and 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?

Usage context is implied through the description's focus on connection states, but there is no explicit statement of when to use this tool versus alternatives. It does not mention exclusions or preferred tools for different situations. For instance, it does not say 'use this to check if authentication is needed' or compare with 'authenticate'. The description gives clear context but lacks explicit guidance on when/when-not to use.

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 many behaviors beyond the annotations, such as invoke working even when the MCP is not installed, returning connect/checkout links and requiring retry, write actions needing workspace owner/admin, and search/describe flagging installed status. It also explains the prompt library's behavior with shareable links that open without login. Annotations only declare openWorldHint, so this additional context is valuable and not contradictory.

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 lengthy but well-structured with 'Core flow', 'KEY', and explicit action distinctions. Every sentence adds value, though some parts could be tightened. For a tool with 14 actions and 23 parameters, this length is acceptable and information-dense.

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 all action areas: search, describe, invoke, install/uninstall, list_tools, subscribe/cancel, report_bug, request_mcp, and prompt library functions. It includes auth requirements, payment/credential edge cases, and installed status flags. With no output schema, it still explains key return behaviors (e.g., connect/checkout links, shareable prompt URLs), making it highly 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 schema has 23 parameters with 0% description coverage, so the description must compensate. It effectively explains the meaning of the action parameter by describing each action's flow and associated parameters (e.g., invoke uses tool_id + arguments, describe uses mcp_id). However, it doesn't detail many parameters like cancel_reason, conversation, or prompt_targets, leaving some gaps for an agent to infer.

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: 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It differentiates from siblings by describing its unique role as a catalog and executor of MCPs, and it outlines the core search→describe→invoke flow, distinguishing it from authentication or system info 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?

Explicit guidance is provided: 'Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile... → invoke RUNS that tool.' It also advises when to use invoke vs install: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT.' It lists alternatives like list_tools for callable tools, and directs to request_mcp when nothing fits.

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 indicate idempotency and non-destructive behavior, and the description adds the specific instruction to include conversation history. It does not elaborate on side effects or outcomes, but given annotation coverage, the added value is modest.

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 concise sentence that states the purpose and a key usage hint. No redundant language or structural issues.

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 output schema, the description covers the main action and reproduction context. However, it lacks details on expected message content or response behavior, making it 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?

Schema description coverage is 0%, so the description must interpret parameters. It only mentions the conversation array, leaving 'message' and 'context' unexplained. This partially compensates but is insufficient for full clarity.

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: reporting bugs, missing features, or feedback. It specifies the target (bug/feature/feedback) and mentions the conversation array for reproduction, distinguishing it from sibling tools like authenticate or marketplace.

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 instructions to include the conversation array for reproduction, but does not explicitly state when not to use it or list alternative tools. Given distinct siblings, the intended use case is inferred.

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 that it shows versions, which is consistent with the readOnlyHint and idempotentHint annotations, adding no contradiction. However, it does not add much beyond what the annotations already imply (read-only, non-destructive). Since the bar is lower with annotations, a 3 is appropriate as it adds minimal but acceptable 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 a single sentence, which is extremely concise and front-loaded with the core purpose. Every word earns its place, making it an example of effective brevity.

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 has no parameters, an output schema is not necessary, and the description covers the essential purpose. The annotations provide safety context. For such a simple tool, the description is complete enough, though it could mention what the output looks like, but that is not critical given the 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?

The tool has zero parameters, and the schema coverage is 100% (empty properties). Based on the calibration, a baseline of 4 is given for 0 parameters. The description does not need to add parameter info as there are none, so this score is justified.

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 the tool shows the current MCP platform and adapter versions, which is specific and distinguishes it from sibling tools like authenticate or connect. However, it could be more explicit about the resource being queried, but it is not a tautology and serves 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?

The tool is a simple read-only version query, and the description implies it should be used when the agent needs to know the platform or adapter versions. There are no alternatives mentioned, but given its simplicity, the context is clear enough. No exclusions are needed.

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 and idempotent hints. The description adds valuable context: payment model (prepaid credits), no credentials needed, data is not confidential, and LGPD responsibility. This goes beyond 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 a single paragraph, reasonably concise, and clearly states the purpose first. It includes extra info (payment, LGPD) but is not overly verbose.

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 and no parameter documentation, the description should clarify expected inputs (CPF/CNPJ) and outputs. It only gives generic info about official sources and payment. This is insufficient for a complete understanding.

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 has 2 params (cpf, cnpj) with no descriptions, and the description does not mention them or explain their roles. It fails to add meaning beyond the schema; the tool's purpose implies CPF/CNPJ, but the description never says so.

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 specifies the tool's function: a query to official Brazilian sources about slave labor ('Trabalho Escravo'). The verb 'consulta' and specific subject matter make the purpose unambiguous, and it distinguishes from siblings which are generic platform 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 provides context (official source, paid per query, no platform credentials) but does not explicitly state when to use this tool versus alternatives. However, there are no overlapping siblings, so the guidance is adequate but not explicit.

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 valuable context about the actual content returned (installed MCPs, connection status, accounts, catalog counts), which goes beyond the annotations and helps the agent understand what to expect. No contradictions.

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 sentence that conveys all necessary information without any waste. It front-loads the purpose and enumerates the specific data returned, making it efficient and easy 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?

For a zero-parameter, read-only informational tool, the description is complete. It states exactly what the output contains (installed MCPs, statuses, accounts, catalog counts), so the agent knows what to expect even without an output schema. No additional details are needed given the 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?

The tool has zero parameters, so the baseline per instructions is 4. The description doesn't need to add parameter details since there are none. The schema coverage is 100% (no properties), so nothing is missing.

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 the tool returns the current toolkit state, listing installed MCPs, connection status, accounts, and catalog tool counts. This clearly distinguishes it from sibling tools like connect, marketplace, and show_version, which are action-oriented. The verb 'returns' and specific resource 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 clearly implies usage for inspecting the toolkit state, which is the only read-only informational tool among siblings. It doesn't explicitly say when not to use it, but the unique nature and contrast with action-oriented siblings (connect, authenticate, etc.) make the intended context clear. No alternatives are named, but none are needed given the tool's specific focus.

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