MPT PB: Certidão Negativa de Feitos

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

The description explains the permanent vs session-only distinction and the browser login flow, adding context beyond the annotations. It does not contradict the idempotentHint or destructiveHint annotations, and clarifies the non-expiring nature of the config-based approach.

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 bit long but every sentence contributes necessary context for the two usage modes. It is structured logically, starting with the login flow, then the two options, and the no-args behavior.

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 absence of an output schema, the description sufficiently covers the tool's purpose and usage. It does not describe return values on success/failure, but for an authentication flow, the steps are clear enough.

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 compensates by explaining the token parameter (as a JWT) and the empty call for retrieving the link. This adds meaning beyond the schema's simple type definition.

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 it is an authentication tool that guides the user through logging in via browser and obtaining an access token. It distinguishes itself from siblings by focusing on login/token acquisition rather than connection or marketplace functions.

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 explicit guidance on two usage modes: permanent configuration via Authorization header and session-only login via token parameter. It also explains the no-args behavior for getting the link. However, it does not mention when not to use this tool or directly compare to alternatives like 'connect'.

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 valuable conditional behavior beyond annotations: the authenticated:true/empty pending[] state versus the connect_url/per-install URL state. A minor gap is that the partial-connectivity case (some providers connected, some not) is not described.

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, front-loaded with the core purpose, then conditional details. Every sentence earns its place with no redundancy or padding — the description is appropriately sized for a parameterless status 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 simple 0-parameter, read-only status tool with robust annotations, the description is nearly complete: it specifies the return shape for the two primary states. The only gap is the omitted middle case (partial connectivity), and since there is no output schema, the description carries the full burden for return-value documentation.

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 100% schema coverage is vacuously satisfied by an empty properties object. Per the rubric, a 0-parameter tool receives a baseline of 4, and there is nothing further the description needs to add about parameter 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 uses a specific verb+resource pair ('Returns connection status and URLs') and clearly defines the output contract for two distinct states (all connected vs. missing credentials). This distinguishes it from siblings like authenticate, which performs the connection action, and show_version/toolkit_info, which report different system facts.

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 described conditional outputs — the agent can infer it is a status-check tool to call before/after authentication. However, there is no explicit guidance on when to use connect versus authenticate, nor any exclusions or alternatives named.

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 (readOnlyHint: false, openWorldHint: true) are minimal and the description carries the full burden of disclosure without contradicting them. It reveals critical non-obvious behavior: 'invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit' — a genuinely surprising behavior an agent must know. It also discloses auth-link and checkout-link responses, side effects of install, and permission boundaries for writes. No contradiction with annotations 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 a dense wall of text (~350 words) with no paragraph breaks, making scannability harder than ideal. However, every sentence earns its place — there is virtually no filler, and critical differentiators (instant-vs-installed, billing links, permissions) are front-loaded near the core flow. The structure could be improved with bullets, but the density is justified given the tool's multi-action surface.

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 an extremely complex tool (14 actions, 23 params, billing, permissions, prompt library), the description is remarkably complete: it covers the happy path, the edge cases (connect links, empty wallet, one-off execution), permission model, and the distinction between cataloged vs. currently-callable tools. The only real gap is parameter-level detail, but conceptually nearly every behavior an agent would need to act safely is disclosed. No output schema exists to offload this burden.

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 all burden falls on the description. It thoroughly explains the semantics of the 'action' parameter values (search/describe/invoke/install/prompt actions) and mentions tool_id ('so you pick the right tool_id'). However, the remaining ~20 parameters (immediate, tier_slug, conversation, arguments, prompt_vars, message, etc.) receive no explanation of format, purpose, or when they're required, leaving meaningful gaps for a 23-param 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 defines the tool as 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' with a specific verb+resource for each capability ('finds MCPs by intent', 'returns one MCP's full profile', 'RUNS that tool'). It distinguishes its sub-flows from sibling tools like list_tools ('lists what is callable right now'). Even the secondary prompt-library feature is precisely delineated by what each action does ('search_prompts finds one, get_prompt returns its full text').

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 with alternatives: 'Use install only to make an MCP PERMANENT in the active toolkit' and 'prefer invoke for a single/occasional use.' It names the core flow ('action=search discovers MCPs by intent → describe returns one MCP's full profile... → invoke RUNS that tool'), states permission context ('require workspace owner/admin'), and even covers retry behavior ('the user opens it, then you retry').

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, so the description doesn't contradict them. The description adds context: it is a paid service with prepaid credit, hosted by the platform, and the data is not confidential. However, it doesn't disclose potential rate limits, response format, or what exactly happens on a successful or failed query. Given annotations cover the safety profile, a 3 is appropriate; description adds some context but not deep behavioral detail.

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 with a clear structure, approximately 40 words. It covers purpose, hosting, payment, and a legal note. It's efficient but could be slightly more front-loaded with parameter clarification. Overall, it's concise and each clause 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 there is no output schema and no parameter descriptions in the schema, the description should provide more context about the parameters and perhaps the response. It does explain the nature of the data (not confidential, same as available to citizens) and the payment requirement. However, without parameter guidance and potential output explanations, completeness is moderate. The tool's complexity is low with only two parameters, so a 3 is reasonable.

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 two parameters, 'cpf' and 'cnpj', both strings, with no description in the schema (0% coverage). The description does not explain the parameters at all. It implies that the certificate can be queried for a person (CPF) or company (CNPJ), but it never explicitly states which parameter corresponds to which. This is a significant gap as the description fails to compensate for the lack of schema documentation.

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 purpose: it queries the official source for a 'Certidão Negativa de Feitos' (negative certificate of legal proceedings) from the Brazilian Public Ministry (MPT-PB). It uses specific verb 'consultar' and names the resource. Although it doesn't explicitly distinguish from sibling tools, which are unrelated platform utilities, the context is clear enough.

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 mentions that it is hosted by the platform, requires prepaid credit, and queries official Brazilian sources, implying it's for obtaining citizen-available data. However, it does not explicitly state when to use this tool vs alternatives, nor does it mention exclusions (e.g., not for sensitive data). Siblings are generic tools, so this tool stands out, but explicit usage guidance is limited.

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 non-read-only, non-destructive, and idempotent. The description adds minimal behavioral info beyond the requirement to include conversation. No mention of side effects, responses, or error states, but bar is lowered by 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?

Two compact sentences with clear, actionable language. No fluff, and the key usage instruction (include conversation) is 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 3-param tool with no output schemachers, the description covers the essentials but omits what happens after reporting, potential side effects, or any return values. It's 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 coverage is 0%, so the description must clarify parameters. It explicitly mentions 'conversation' and its purpose, and 'message' is implicitly the bug report content. However, 'context' is left unexplained, and no parameter format details are given.

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 action:

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?

Gives explicit instruction to include the conversation array for reproduction, but doesn't specify when to use versus alternatives. However, since siblings are unrelated, the context is 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?

The description aligns with the provided annotations (readOnlyHint=true, idempotentHint=true), and the verb 'Show' reinforces the non-destructive nature. However, it does not disclose any additional behavioral aspects beyond what annotations already convey, which is acceptable given the annotations' completeness.

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 extremely concise and to the point, using only a single short sentence. It avoids any unnecessary details or filler, making it easy for an agent to understand the tool's primary purpose at a glance.

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 retrieval tool, the description is complete. It states exactly what information is provided (MCP platform and adapter versions) and implies no side effects or complex behavior. No output schema is present, so the description sufficiently covers the tool's function.

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 of 4 applies. The description does not need to elaborate on parameters since none exist, and the description itself implies that no input is required, which is consistent with its function.

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: retrieving current MCP platform and adapter versions. The action verb 'Show' directly indicates a read-only retrieval, and the object is well-specified, leaving no ambiguity about what the tool does.

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 no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, typical scenarios, or circumstances where it might be inappropriate. This lack of context could leave agents uncertain about selecting it.

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 well-covered. The description adds useful behavioral context by specifying what 'state' includes (installed MCPs, connection status, accounts, tool counts), which goes beyond the annotations. It does not contradict annotations and provides sufficient transparency.

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 essential information without fluff. It is front-loaded with the primary action and then details the return content. No redundant or filler text; every clause earns its place.

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, so the description must convey what the return value contains. It lists the key components (installed MCPs, status, accounts, catalog tool counts), which is sufficient for an agent to understand the tool's purpose and likely output. It does not specify the exact format (e.g., JSON structure) or whether results are paginated, but for a read-only overview tool, the level of detail is adequate.

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 description coverage is 100% (trivially). Baseline for no parameters is 4. The description does not need to explain parameter semantics, and the lack of parameters is clear from the schema. No additional parameter explanation 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's function with a specific verb and resource: 'Returns the current toolkit state' and enumerates the exact contents (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from siblings like show_version (version) or marketplace (marketplace context).

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 toolkit state but does not explicitly state when to use it over alternatives or provide exclusions. For example, it could mention 'Use this to inspect the overall health of your toolkit connections' but it doesn't. The context is clear enough that an agent would infer when to call it, but explicit guidance is missing.

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