DETRAN MA: Impressão de CRLV

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

The description goes beyond the annotations by explaining two key behaviors: returning a browser link when called with no args and accepting a JWT token to establish a session. It also adds context about permanent, non-expiring vs. session-only authentication. The main omission is a clear statement of what happens on success or failure, but the existing disclosure is still solid.

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 packs multiple pieces of information into a single paragraph but remains dense without redundancy. The structure could be improved with clearer separation between the config-based method, the session-based method, and the no-argument shortcut, but no sentence is wasted.

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 authentication tool with no output schema, the description gives a usable workflow: when to call with a token, when to call without, and how to configure a permanent connection. It does not explicitly describe the response format beyond 'get the link', but the overall guidance is sufficient for an agent to invoke the 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?

Despite the input schema having only a bare token property with zero description coverage, the description fully explains the token's meaning and how the caller should supply it. It distinguishes between pasting the token as { token: '<jwt>' } and omitting it to receive the login link. This completely compensates for the missing 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 tool's purpose: authenticating to MCP.AI by logging in in the browser and obtaining an access token. It specifies the main resource (MCP.AI) and distinguishes the tool from unrelated siblings like marketplace or show_version. The verb 'log in' and the authentication flow leave no ambiguity.

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 modes: adding the token to server config for a permanent connection, or passing a token for session-only login. It also explains that calling with no arguments returns the login link, providing a clear decision path for the agent. This is strong usage guidance even without naming sibling alternatives.

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 provide readOnlyHint=true and idempotentHint=true, so the safe, non-destructive nature is clear. The description adds context about the output structure when all providers are connected vs. missing credentials, which is useful. However, it does not explain what happens if some providers are connected and others are not, or the exact format of per-install URLs, leaving some ambiguity.

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, concise and front-loaded with the primary purpose. It includes conditional behavior without excessive detail. Slight deduction for not specifying the shape of 'connect_url' or 'per-install URLs', but the structure is efficient.

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 simple with no required parameters and no output schema, so the description does not need to document parameters or return types. It covers the key scenario of all-connected vs. missing credentials, but omits edge cases like partial connectivity or the exact JSON structure of the response. Given the simplicity, it is adequate but could be more explicit about the full set of possible states.

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 no parameters, there is nothing to document, and the context signal indicates 100% schema description coverage (trivially, as there are no parameters). The description focuses on the return semantics, which is appropriate. Since there are no parameters, a baseline of 4 is reasonable.

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 returns connection status and URLs, distinguishing it from siblings like 'authenticate' by focusing on status rather than action. It specifies the behavior under different conditions (all connected vs. missing credentials), which is more specific than a mere 'check status'.

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 connection status, which is a read-only operation, aligned with the annotations. However, it does not explicitly compare to alternatives like 'authenticate' or 'toolkit_info', leaving the agent to infer when to use this tool over others. No when-not-to-use guidance is provided.

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 meaningful behavioral details beyond the readOnly and idempotent annotations: it mentions prepaid credit payment, official data source, non-confidential nature, and LGPD responsibility. This enriches the agent's understanding of the tool's operational and legal context without contradicting 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 concise, consisting of three sentences, and is front-loaded with the primary purpose. Every sentence adds relevant context (purpose, payment, data source, legal) without redundancy or unnecessary detail.

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 sufficiently covers the tool's core purpose, payment mechanism, official sourcing, and legal compliance. While it does not specify output format or error handling, for a simple CRLV query tool the provided context is adequate, though it could mention expected output (e.g., document PDF).

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 provides no elaboration on the three required parameters (placa, renavam, documento_proprietario). Since the schema lacks any descriptions, the description fails to compensate for the low schema coverage, leaving parameter meaning entirely unaddressed.

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: printing CRLV documents and consulting an official source. It explicitly names the resource (CRLV) and the action (consulta/impressão), distinguishing it from the generic platform-level 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 purpose implies usage for CRLV retrieval, but the description does not explicitly state when to use this tool over alternatives or provide usage scenarios. It conveys the context of an official, prepaid query, but lacks direct 'use this when' 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?

Goes far beyond annotations by revealing invoke's one-off behavior even when MCPs are not installed, the credential/wallet fallback links, workspace owner/admin write permissions, and the installed_in_toolkit vs workspace flags. Prompt library behavior (link not requiring login) is also disclosed. 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 long but densely informative and logically structured, starting with the core concept and flowing through key behaviors, permissions, and prompt library. Every sentence adds value, though the length could be slightly overwhelming for quick scanning.

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?

Covers most of the 14 actions and main behaviors, including auth, billing, permissions, and prompt library. However, the 'resume' action and some parameters (immediate, conversation, tier_slug) are not mentioned. For a highly complex tool with no output schema, this is still a very high degree of 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 has 0% description coverage, so the description must compensate. It does explain the meaning of key parameters through workflow descriptions (action, mcp_id, tool_id, arguments, query, limit, prompt_*), but several params like 'immediate', 'tier_slug', 'conversation', and 'resume' are not explicitly described. Slightly incomplete, but strong overall.

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 role as 'the official mcp.ai marketplace' and 'the way to run' MCP/tools, with specific verbs like 'search', 'describe', 'invoke', and 'install'. It distinguishes itself from sibling tools by covering catalog discovery, invocation, installation, billing, and prompt library in one place.

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 an explicit core flow (search → describe → invoke) and contrasts invoke vs install: 'prefer invoke for a single/occasional use' vs 'use install only to make an MCP PERMANENT'. Also explains when to use list_tools, subscribe/cancel, report_bug, request_mcp, and the prompt library functions. This is model-level usage 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 adds some behavioral context by instructing the agent to include the conversation array for reproduction. Given annotations already communicate readOnly=false, idempotentHint=true, and destructiveHint=false, the description does not need to restate those. However, it does not disclose what happens after submitting, such as external transmission or whether confirmation is returned.

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 with no filler. The first sentence states purpose, and the second provides the key usage instruction. Every phrase 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?

For a simple feedback tool with no output schema and only three parameters, the description gives a functional overview and one usage tip. However, the conversation type mismatch and lack of parameter-level details mean the agent may not construct the request correctly without further inference.

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, but it only explains the conversation parameter, and even that is imprecise: it calls it an "array" while the schema declares it as a string. The required "message" parameter and the optional "context" parameter are left implicit and undocumented.

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?

Description clearly states the tool's purpose: "Report a bug, missing feature, or send feedback." This is a specific verb plus resource and is distinct from sibling tools like authenticate, connect, and show_version.

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: when the user wants to report a bug, request a missing feature, or send feedback. It also gives a practical instruction to include the conversation array for reproduction, though it does not explicitly mention when not to use it or name alternatives.

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, so the read-only nature is covered. The description adds no extra behavioral details beyond what annotations provide (e.g., return format). Given that annotations carry the safety profile, the description does not need to repeat it, and 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 a single, concise sentence that conveys the entire purpose without filler. It is front-loaded and wastes no words.

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, no output schema, and a trivial read-only function, the description fully satisfies the need. No additional context (like error handling) is necessary given the simplicity. The annotations cover safety, and the description covers purpose.

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 0 parameters, and schema description coverage is 100% (trivially, no properties). The baseline for zero parameters is 4; nothing is needed from the description. The description adds no parameter details because none exist.

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?

Description clearly states the tool's action: 'Show the current MCP platform and adapter versions.' The verb 'Show' plus the specific resource ('MCP platform and adapter versions') makes the purpose unambiguous and distinguishes it from siblings like connect or authenticate, which have different objectives.

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 obvious use case—whenever version information is needed. It does not explicitly mention alternatives or exclusions, but for a simple zero-parameter version tool, this level of guidance is sufficient. No competing tool among siblings serves the same purpose.

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, establishing this as a safe read operation. The description adds value by detailing exactly what state is exposed (installed MCPs, connection status, accounts, catalog tool counts), which goes beyond what the annotations convey. This is exactly the kind of additional context that helps an agent understand what to expect. No contradiction with annotations; description aligns with read-only, idempotent 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?

One sentence, 20 words, front-loads the action verb 'Returns' and packs in all key details: toolkit state, MCPs, connection status, accounts, and catalog tool counts. Every word earns its place; no fluff, no redundancy. Excellent example of a concise yet information-dense description.

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, idempotent tool with no output schema, the description covers the functional contract well. It explains what the tool returns in enough detail for an agent to decide when to call it. A small deduction because it doesn't mention the exact structure or format of the response (e.g., is it a list or map?), though the description's list of fields is reasonably complete for decision-making. The presence of sibling tools like show_version and authenticate suggests this tool is the primary state query, which is clear from the 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?

With 0 parameters, the schema is trivially complete at 100% coverage. The description correctly doesn't invent parameters and instead focuses on the return value, which is the right call. For a parameterless tool, the description's job is simply not to add confusion, and it succeeds. Baseline 4 for 0 params, upgraded to 5 because the description effectively communicates the output semantics, which is the only thing to get right here.

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 returns the current toolkit state, listing specific elements: installed MCPs, connection status, accounts, and catalog tool counts. While it doesn't explicitly contrast with siblings, the level of detail (installed MCPs, connection status, accounts, catalog tool counts) makes the purpose unambiguous and distinguishes it adequately from the sibling tools 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 this is the go-to tool for state/status queries, but doesn't explicitly state when to prefer it over siblings like show_version or authenticate. It provides clear context on what information is returned but lacks explicit when/when-not guidance or alternative tool mentions, which would be useful given the toolkit context.

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