Dossiê de Crédito Completo

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

It discloses behavior beyond annotations: no args returns a link; token performs a session login; config-based header provides a permanent non-expiring connection. This adds meaningful context to the idempotent and non-read-only 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 information-dense but slightly run-on, mixing user instructions (add to config) with tool call semantics. While every sentence earns its place, it could be better structured into separate steps for clarity.

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 single-parameter tool without an output schema, it covers all main usage scenarios: link generation, token submission, and config-based permanent connection. However, it does not specify what the tool returns on a successful token submission, leaving 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 description explains the optional 'token' parameter as a JWT pasted by the user, and clarifies that omitting it returns the login link. With 0% schema description coverage, this fully compensates for the schema's lack of parameter 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 this is an authentication tool for MCP.AI IDE agents, explaining the login flow and token handling. It distinguishes itself from siblings by focusing on token acquisition and session vs. permanent configuration.

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: call with no args to get a login link, or with a token (JWT) for session-only login. It also recommends adding the token to the server config for a permanent connection, giving clear alternatives and when to use each.

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, but the description adds meaningful behavioral context: the exact return states ('authenticated:true', empty pending[], connect_url) and the existence of per-install URLs. This goes beyond the structured data and enhances 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 then adds conditional details. Every word contributes value; no redundancy or filler.

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 status tool, the description fully covers the key behavioral states (connected vs. missing credentials) and return URL semantics. The sibling list and annotations fill in any remaining context, making the description complete for 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 tool has zero parameters, so schema coverage is trivially complete. The description doesn't need to explain parameters, and the baseline of 4 applies due to the absence of parameters. No additional param info 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 connection status and URLs', which is a specific verb+resource. It distinguishes itself from the sibling 'authenticate' by focusing on status rather than performing authentication, and it mentions 'authenticated:true' to align with the auth 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 explains conditional behavior based on connection state (all providers connected vs. missing credentials), which implies usage for checking whether authentication is needed. It provides clear context but does not explicitly state 'use this to check before authenticating' or mention exclusions relative to siblings.

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 read-only, idempotent, and non-destructive. The description adds valuable context: the tool is hosted by the platform, requires no credentials, consumes prepaid credit, queries official bureaus, and imposes LGPD obligations on the caller. This goes well 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 five sentences and front-loaded with the core purpose. It includes necessary legal and billing context, but the legal clauses could be condensed. Still efficient and well-structured.

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 no output schema and the complexity of credit data, the description covers purpose, cost, legal basis, and data sources. However, it omits parameter guidance (especially the odd both-required schema) and does not explain the 'completo' flag, leaving notable gaps for correct 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?

Schema description coverage is 0% and the description never mentions Cpf, Cnpj, or 'completo'. It leaves the agent uncertain which parameter identifies an individual vs a company, and why both CPF and CNPJ are required. The description should at least map 'pessoa física' to Cpf and 'pessoa jurídica' to Cnpj.

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 a complete credit dossier (registration data, risk score, outstanding issues) for individuals or companies, and explicitly says it queries credit bureaus. This distinguishes it from sibling tools (authenticate, connect, marketplace) which are platform-level operations.

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: it is a paid query (prepaid credit), requires a legal basis under LGPD, and the caller is responsible for purpose. It does not name alternatives, but the legal and cost constraints serve as implicit guidance on when to use 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 only provide broad hints (readOnlyHint=false, openWorldHint=true). The description adds crucial operational details: invoke works even when the MCP is not installed, it is one-off, returns connect/checkout links on auth/billing issues, and writes require owner/admin. 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 long but information-dense; it front-loads the core purpose and then systematically explains actions and edge cases. Each clause earns its place, though the text is a single block with occasional phrasing ('pontualmente') that breaks flow slightly.

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 highly complex tool with no output schema and minimal annotations, the description covers the major flows, side effects, billing, auth, and the separate prompt library. However, it omits the 'resume' action and does not describe the return format of each action, leaving some gaps for an agent to infer.

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 compensate. It explains the action parameter's role and the significance of tool_id through the flow, but leaves many params (limit, query, immediate, tier_slug, cancel_reason, prompt_vars, etc.) without explicit semantic detail. Partial compensation, but not enough for a 23-parameter 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 immediately identifies the tool as 'the official mcp.ai marketplace' and presents a clear core flow (search → describe → invoke), distinguishing it from specialized siblings. It also covers the separate prompt-library feature, so the overall purpose is 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?

The description gives explicit guidance: 'prefer invoke for a single/occasional use' and 'use install only to make an MCP PERMANENT'. It also explains when list_tools, subscribe/cancel, and prompt actions are appropriate. However, it does not reference sibling tools like authenticate or connect, so cross-tool alternatives are only implied.

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 idempotentHint: true, readOnlyHint: false, and destructiveHint: false, so the safety profile is known. The description adds the instruction to include the conversation array for reproduction, which is useful behavioral context, but it does not disclose what happens after submitting (e.g., ticket creation or external side effects). 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 only two sentences, with the first stating the purpose and the second giving a specific usage instruction. Every sentence earns its place, with no redundancy or fluff.

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 tool is relatively simple (3 params, no output schema), but the description could be more complete. It covers purpose and gives guidance for the 'conversation' parameter, but does not explain the required 'message' field or any return/behavior after reporting. This leaves some gaps, especially given the low schema 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?

Schema description coverage is 0%, so the description must compensate. It explains the 'conversation' parameter as the array for reproduction, but leaves 'message' (the required parameter) and 'context' largely implied. The required message is reasonably inferred from the tool's purpose, but not explicitly described.

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 'Report' and names the resource as 'a bug, missing feature, or feedback', which directly and unambiguously identifies the tool's purpose. This clearly distinguishes it from the sibling tools, all of which are unrelated (auth, marketplace, version info, 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?

The description clearly states what the tool is for ('Report a bug, missing feature, or send feedback'), providing enough context for when to use it. It does not explicitly mention when-not-to-use or list alternatives, but the sibling tools are so unrelated that no confusion is likely. This meets the 'clear context, no exclusions' level.

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 disclose the safety profile. The description adds context about what versions are shown (MCP platform and adapter), which is useful beyond the structured annotations. However, it does not describe output format or any potential side effects, though given the hints, none are expected.

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, complete sentence that is immediately understandable and contains no extraneous words. It is perfectly concise while conveying the necessary 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?

For a simple version-information tool with no parameters and no output schema, the description fully captures what the tool does. The annotations complement it by declaring non-destructive, read-only behavior. No further details are necessary for an agent to select and invoke this tool 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?

There are zero parameters, so the baseline is 4. The description does not need to explain parameter semantics, and no additional parameter information is required or provided.

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' and clearly identifies the resource: current MCP platform and adapter versions. This is unambiguous and distinct from sibling tools like authenticate or toolkit_info, though it could be more explicit about differentiating from toolkit_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 (when version information is needed) but provides no explicit guidance on alternatives or when not to use. Sibling tools like toolkit_info may also provide informational output, but no differentiation is mentioned, so the guidance is merely implied.

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 covers safety and side-effect concerns. The description adds context about the returned state (which MCPs are installed, connection status), but does not disclose additional operational behaviors like authentication requirements or error conditions.

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, front-loaded sentence that lists the output contents concisely. Every word adds information; no 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 has no parameters and no output schema, the description adequately explains what the tool returns by listing the key components. It could have specified the response format more precisely, but for a simple info tool it 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?

The input schema has no parameters, so there is nothing to document. Baseline for zero parameters is 4. The description correctly implies the tool needs no configuration.

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 and enumerates the specific components (installed MCPs, connection status, connected accounts, catalog tool counts). This distinguishes it from sibling tools like 'show_version' which focuses on version, and 'authenticate' which handles auth.

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 the tool is used to inspect overall toolkit state, but does not explicitly state when to use it versus alternatives or provide exclusions. It offers clear context of what the tool does, but lacks direct comparison to sibling tools.

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