ECRVSP Documentos: Baixar Veículo

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

Annotations include idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description explains the behavior: it provides a login link or accepts a token, and mentions the permanent vs session-only distinction. However, it does not disclose what happens after authentication (e.g., whether it changes server state) or whether multiple calls are needed. Since annotations don't contradict, and the description adds some behavioral context (e.g., non-expiring config vs session), a 3 is appropriate.

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 somewhat long but contains necessary information. It starts with target audience and action, then details both login methods. The sentence structure is clear, though it could be slightly more compact by using bullet points or splitting into two sentences. No fluff, each 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?

Given the tool's complexity (two authentication modes) and absence of output schema, the description covers the workflow well: how to get the link, how to use the token, and the permanent vs session comparison. It does not specify the output format (e.g., whether it returns a success message), but for an authentication tool, this is acceptable. The description is complete enough for an agent to decide when and how to call it.

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 one parameter 'token' with 0% description coverage. The description explains what the token is ('<jwt>') and when to pass it (after user pastes), and also mentions calling with no args to get the link. This adds significant semantic value beyond the schema, which is just a string type. The description compensates for low schema coverage, hence 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 clearly states the tool's purpose: to authenticate for MCP.AI in IDEs like Cursor. It specifies the resource (MCP.AI for IDE agents) and the action (log in via browser and copy access token). It distinguishes from siblings by mentioning IDE agents specifically, though sibling differentiation is not explicit.

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 two clear usage paths: permanent login via config header or session-only login via token parameter. It explicitly instructs when to call with no args to get the link and when to use the token param. It also implies when not to use this tool (e.g., for other connection methods), and recommends the best approach (adding to config).

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 agent knows this is a safe read operation. The description adds the behavioral detail about returning connect_url when credentials are missing, which is useful. However, it doesn't describe the exact structure of the response beyond the mentioned fields, but given the annotations cover safety, this is adequate.

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 core purpose, and every sentence adds value. It efficiently explains the two possible outcomes 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 has no parameters, no output schema, and annotations cover safety, the description is complete enough. It explains the return values in both states, which is the main thing an agent needs to know. It could mention the format of URLs or the meaning of 'pending' but that's minor 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, and schema description coverage is 100% (vacuously). The description adds meaning by explaining what the tool returns in different states, which is the key semantic content. Since there are no parameters to document, the description effectively covers the tool's 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, and explains the two possible states (all connected vs. missing credentials). It distinguishes from siblings like authenticate and toolkit_info by focusing on status/URLs rather than performing authentication or showing version 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 it (to check connection status and get URLs when credentials are missing) but does not explicitly state when not to use it or mention alternatives. It provides context about the two states but lacks explicit guidance on choosing between this and authenticate or toolkit_info.

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 significant context beyond annotations: it reveals a prepaid credit payment model, states no platform credentials are needed, clarifies the data is from official Brazilian sources and not confidential, and mentions LGPD compliance responsibilities. These are valuable behavioral disclosures not covered by annotations, which only indicate read-only and idempotent hints.

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 of moderate length with a mix of functional, commercial, and legal information. It is not overly verbose, but the content is not well-structured and could be more front-loaded with a clearer action statement. Some sentences (e.g., about LGPD) are important but add length without improving usability.

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?

With 11 parameters, no output schema, and zero parameter explanation, the tool is incompletely specified. The description does not clarify what the tool returns (e.g., a PDF file, data fields) or how the payment/credentials work operationally. The annotations cover read-only and idempotency, but the overall context is insufficient for an agent to use this tool reliably.

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 provides no explanation for any of the 11 parameters. Parameters like 'a3', 'a3_pin', and 'numero_espelho' remain cryptic with no additional meaning. The description does not compensate for the lack of schema documentation, leaving the agent unable to correctly fill the required fields.

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 states 'Baixar Veículo, consulta em fonte oficial' (Download Vehicle, query in official source), giving a general sense of querying vehicle data. However, it's vague about the exact operation (whether it downloads a PDF or returns data) and doesn't clearly distinguish from any alternatives, though sibling tools are unrelated. The purpose is not a tautology but lacks precision.

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?

No guidance is provided on when to use this tool versus alternatives. The description mentions it queries official Brazilian sources and is paid, but it does not state specific use cases, prerequisites, or exclusions. There are no similar vehicle-query tools among siblings, so situational guidance is absent.

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 far beyond the provided annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) by detailing key behaviors: invoke runs uninstalled MCPs one-off without bloating the toolkit, returns connect links for credentials and checkout/top-up links for empty wallets, and requires owner/admin for writes. It also clarifies the installed_in_toolkit vs installed_in_workspace distinction and the prompt-library 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 long but front-loaded with the core flow, and every major behavioral clause earns its place given the tool's 14 actions and 23 parameters. It is structured as a dense stream rather than bullet-pointed sections, which slightly hurts scannability, but the content is well organized around search/describe/invoke, install, billing, writes, and the prompt library.

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?

Despite having no output schema, the description covers the essential operational semantics: what each action category returns or causes, how invoke handles uninstalled MCPs, what to do when credentials or payment are needed, how install differs from invoke, and how the prompt-library actions behave. For a tool this complex, this level of contextual explanation is strong.

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 does explain the main action enum, mcp_id, tool_id, arguments, and the prompt publish/get flow, adding real meaning beyond raw field names. However, several parameters (limit, immediate, tier_slug, request_name, request_details, cancel_reason, conversation, prompt_targets, prompt_category, prompt_description) remain unaddressed and only inferable from their names or action context.

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 identifies the tool as the official mcp.ai marketplace covering discovery, description, invocation, installation, billing, and prompt-library actions. It names distinct verbs and resources (search, describe, invoke, install, list_tools, search_prompts) and explains the overall core flow, making it easy to distinguish from sibling tools like authenticate or report_bug.

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 usage guidance: use search → describe → invoke for one-off needs, prefer invoke over install for occasional use, use install only for permanent toolkit membership, and use subscribe/cancel/report_bug/request_mcp for their specific purposes. It also explains auth/payment retry behavior and workspace-owner requirements, which helps the agent decide when this tool is appropriate.

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 annotations (idempotentHint: true), and the tool doesn't appear to be destructive or read-only. The description adds context that the conversation array should be included for reproduction, which is a practical detail beyond the structured fields, but it doesn't provide additional clauses about side effects or rate limits. Given that annotations are present and there's no contradiction, this seems appropriate.

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, focused and efficient. The first sentence states the purpose; the second provides the most critical usage detail. It is short and to the point, although it could have used the saved space to clarify the remaining parameters, which would have been more beneficial.

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-parameter tool with no output schema, the description covers the main purpose and the most important usage guideline (including conversation for reproduction). It's reasonably complete for a tool of this complexity, though it leaves room for more detail on the 'context' parameter.

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?

Since schema description coverage is 0%, the description was expected to compensate. It does explain the `conversation` parameter's purpose, but it doesn't elaborate on `context` or `message`. The instruction to include transcript data helps the agent understand the purpose of at least the conversation parameter, providing some value beyond the raw 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 names a clear action ('Report') and specific resources ('a bug, missing feature, or send feedback'), which precisely distinguishes it from siblings like `show_version` or `authenticate`. The overall purpose is immediately understandable and non-tautological.

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 defines what should be sent through the tool ('a bug, missing feature, or send feedback'), which effectively separates it from sibling tools that do other things like authenticate or show version. It provides a specific example of usage guidance ('Include the conversation array with recent messages for reproduction'), which helps the agent know how to construct a useful request. However, it doesn't explicitly name alternative tools to use in other cases, hence the slightly lower score.

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 report readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description reinforces this by stating 'Show', but it does not add extra behavioral details such as output format or potential exceptions. Per calibration, this is baseline-appropriate for annotation-covered tools.

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, front-loaded declarative sentence with no filler. Every word earns its place and the structure makes the tool instantly 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, no-side-effect tool with no output schema, the core behavior is communicated. Could slightly enhance by describing what the return value looks like, but the overall context is sufficiently complete for a zero-parameter 'Show version' type 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 has zero parameters, so an input schema is essentially nonexistent; the baseline of 4 for a no-parameter tool is applied. The description is clear because it explains the purpose without needing parameter-specific semantics.

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 names the exact resources: 'current MCP platform and adapter versions'. This clearly distinguishes the tool from siblings 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?

The description implies the tool is meant for checking versions, but it does not provide explicit 'when to use' guidance or contrast with sibling tools like toolkit_info. Adding a note about when to use this versus alternatives would improve selection.

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, destructiveHint=false, idempotentHint=true, so the description only needs to add context beyond that. It does so by detailing the exact contents of the returned state, providing useful information about what the tool exposes without repeating safety traits.

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, front-loaded sentence that efficiently enumerates all returned data. No extraneous words or repetition of schema/annotations.

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 (no params, no output schema, clear read-only intent), the description fully covers what the tool does and returns. It is complete and self-contained.

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 has no properties (100% coverage). With no parameters to explain, the baseline is 4. The description adds no parameter-specific information, but none is needed.

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 current toolkit state, listing specific components (installed MCPs, connection status, connected accounts, catalog tool counts). This distinguishes it from sibling tools like show_version (version info) and action tools like connect or 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 description implies usage context: to check the overall state of the toolkit. It doesn't explicitly mention alternatives or when not to use, but the read-only nature and comprehensive scope make it self-explanatory. No exclusions are needed since it's a standalone info tool.

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