DER PR: Certidão Negativa de Débitos (por placa)

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

Annotations already indicate the tool is idempotent and not read-only, so the description adds valuable behavioral context by explaining the permanent vs. session-only connection semantics and the fact that the permanent header approach does not expire. It stops short of describing what the tool returns after accepting a token or how failures are surfaced, but it provides meaningful 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 compact and front-loaded with the tool's essential login purpose, followed by the two recommended usage paths. It is slightly dense because it bundles setup/config instructions with invocation behavior, but every sentence provides necessary guidance without padding.

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 schema, annotations, and lack of output schema, this description covers the essential invocation paths, token semantics, and session vs permanent connection distinction. It does not explicitly describe what the agent should expect in the response after submitting a valid token, but the overall guidance is sufficient for an agent to select and 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?

The schema has one optional string parameter with no per-parameter description, and the tool description compensates by explaining the token is a JWT pasted by the user and how to call with or without the token. It gives a concrete invocation shape: `{ token: "<jwt>" }` or no args to get the link, which substantially enriches the 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 clearly identifies the tool as the authentication/login mechanism: log in in the browser, copy the access token, and pass it back for a session-only login or no args to get the login link. It distinguishes the tool from common sibling operations by focusing on browser-based auth rather than generic connection handling, though it does not explicitly name a sibling as the alternative.

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 instructions and options: recommending permanent header configuration for non-expiring access, versus session-only login via pasting a JWT, and when to call with no arguments to retrieve the link. This is strong when-to-use and how-to-use guidance, with clear alternative paths based on desired persistence.

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 no destructive action, so the description doesn't need to repeat that. It adds behavioral info about output states (authenticated:true, empty pending[]) and what happens with missing credentials. However, it doesn't clarify if there are network calls or side effects beyond reading status. Since annotations cover safety, it adds some value.

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, concise and to the point. It front-loads the main purpose and then details the behavioral outcomes. No 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?

For a zero-parameter read-only status tool with good annotations, the description is quite complete. It explains the state of connections and the URLs returned. The absence of an output schema is compensated by the description's detail on what is returned. Could add what happens if some but not all providers are connected, but the description already covers missing credentials.

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 zero parameters, so the description doesn't need to explain parameters. It does explain the return values in terms of connection status and URLs, which is useful. Since there are no params, baseline is 4; the description fully explains what the tool returns without needing param 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 explicitly states the tool's purpose: returning connection status and URLs. It adds detail about the states (authenticated:true, empty pending[], missing credentials, connect_url for toolkit and per-install URLs). However, it could better distinguish from siblings like authenticate or marketplace, but it does mention credentials and connection 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: use it to check connection status and obtain URLs for connecting missing providers. It doesn't explicitly say when NOT to use it or alternative tools, but it gives clear context on what it returns. Sibling tools like authenticate seem related, but the description provides enough context to infer when to call 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?

The description goes beyond the annotations by detailing payment requirements, the official nature of the data, non-confidentiality, and LGPD compliance. This adds significant transparency about the tool's behavior and legal responsibilities.

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 relatively concise but includes repetition (e.g., 'consulta em fonte oficial' and 'consulta informação de fontes e órgãos oficiais brasileiros'). It is structured as a single, readable paragraph.

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 the lack of an output schema, the description provides sufficient context about the data source, legal implications, and payment model. It does not cover the 'endereco' parameter, which is a notable omission, but overall it gives a reasonable understanding of the tool's operation.

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 (placa and endereco) with no descriptions. The description only mentions 'por placa' and completely omits 'endereco', providing no semantic guidance for either parameter. This is a major gap given the 0% schema coverage.

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 query negative debt certificates by license plate from official sources. It is distinct from sibling tools like authenticate, connect, and 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 explains that the tool is a paid query using pre-paid credit and does not require platform credentials, implying when to use it (for checking debts). However, it does not explicitly mention alternative tools or specify exact scenarios beyond the general query context.

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?

Despite annotations being sparse (only readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description goes well beyond them: it discloses that writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin permissions, that invoke works even when the MCP is not installed and does not bloat the tool list, and the credential (connect link) and payment (checkout/top-up link) edge cases. This is rich behavioral context the annotations do not provide.

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 continuous run-on paragraph with no section breaks, bullet lists, or bolding, spanning roughly 250 words across three distinct feature clusters. It is information-dense but nearly unparseable at a glance; the key install-vs-invoke guidance is sandwiched in the middle. Structure is the single biggest weakness.

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 extreme complexity — 14 actions, 23 parameters, no output schema, no param descriptions — the description is unusually thorough in coverage: it describes the search→describe→invoke pipeline, auth requirements, one-off execution semantics, the prompt library, and billing actions. But the comprehensiveness is undermined by poor organization, and for such a multi-surface tool the absence of parameter semantics and action-by-action detail makes it incomplete despite its length.

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 23 parameters at 0% schema description coverage, the description carries heavy responsibility. It explains the core orchestration parameters (action values, mcp_id, tool_id, arguments) and the flow, plus the search_prompts/get_prompt/publish_prompt cluster. However, many parameters (immediate, tier_slug, conversation, report_context, prompt_targets, cancel_reason, etc.) receive no explanation in the prose, leaving significant gaps in what each parameter means or when it applies.

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 does state the tool's purpose — it's both a catalog and a runner for MCPs, plus a prompt library. However, it's split across three domains (MCP discovery/execution, installs/billing, prompt library) with 14 distinct actions, making the core purpose diffuse rather than a crisp single verb+resource. It does distinguish from siblings by naming list_tools, report_bug, and the search/describe/invoke flow.

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?

There is genuinely explicit guidance in the middle: 'prefer invoke for a single/occasional use' versus 'use install only to make an MCP PERMANENT', plus when invoke returns a connect link or checkout link and to retry after. list_tools is defined as what is callable right now. The guidance is strong but buried inside an unstructured wall of text, and not all 14 actions receive when-to-use instructions.

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 idempotentHint=true and destructiveHint=false, suggesting a safe, non-destructive operation. The description adds that it requires a conversation array for reproduction, which is useful behavioral context. It doesn't mention response behavior or side effects, but given the annotations, the description adds some extra value without contradiction.

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, focused sentence that covers the core purpose and the key parameter guidance. It is front-loaded with the action and includes the critical instruction about the conversation array. No redundant 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?

The tool is relatively simple with 3 parameters, no output schema, and one required field. The description provides enough context for basic use and the key reproduction detail. It lacks full parameter coverage (context is unexplained), but the core usage is clear for a feedback tool. Given the straightforward nature, the description is sufficiently complete for an agent to select and invoke it 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?

The schema has 0% description coverage, so the description must compensate. It mentions the 'conversation' parameter ('Include the conversation array with recent messages for reproduction') and indirectly references the 'message' parameter as the main content. However, it doesn't explain the 'context' parameter, which is included in the schema but not addressed in the description. Since the description covers two of three parameters, it provides partial compensation.

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 the tool's purpose: 'Report a bug, missing feature, or send feedback.' This is a clear verb (report/send) with specific resource types (bug, missing feature, feedback), and it implies a single action. It doesn't explicitly distinguish from siblings, but the sibling list doesn't include similar feedback tools (e.g., 'authenticate', 'connect', 'marketplace'), so it stands out adequately.

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 says when to use it (when reporting a bug or sending feedback) and hints at what to include (conversation array with messages). However, it doesn't provide explicit exclusions or alternative tool references. There is no guidance on when not to use it, but given the simple nature and no obvious overlap, this is acceptable.

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, non-mutating operation. The description adds no additional behavioral context beyond what annotations provide, but it does not contradict them. Given the annotations cover the safety profile, 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 fully conveys the tool's purpose with no wasted words. It is front-loaded and appropriately sized for a simple read-only 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?

Given the tool's simplicity (no parameters, no output schema, read-only annotations), the description is complete enough. It tells the agent exactly what the tool does. The lack of output schema details is acceptable because the tool likely returns version strings, which is self-explanatory.

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 does not need to explain parameters since there are none. The baseline for zero-parameter tools is 4, and the description is sufficient.

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: showing current MCP platform and adapter versions. It uses a specific verb ('Show') and resource ('MCP platform and adapter versions'), which is clear and distinguishes it from siblings like 'toolkit_info' 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?

The description implies usage context (when you need to check versions) but does not explicitly state when to use this tool versus alternatives. Sibling tools like 'toolkit_info' might also provide version info, but no exclusions or alternatives are mentioned.

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, and idempotentHint=true, so the safety profile is covered. The description adds value beyond annotations by specifying the exact content of the returned state (connection status, linked accounts, catalog counts), which tells the agent what to expect from the call. 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?

One sentence, ~20 words, front-loaded with the action verb and immediately enumerating the delivered content. Zero filler, every clause adds specific value about what the state report includes.

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 inspection tool with rich annotations (readOnly, idempotent, non-destructive, closed-world), the description is largely sufficient. It lists all four categories of returned information. It could marginally note whether an authenticated session is required (given siblings include authenticate/connect), but with the strong annotation coverage and no output schema, this 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?

Zero parameters, so description cannot add parameter-level meaning — per rubric this is baseline 4. The no-input nature is implicitly confirmed by the description presenting this as a pure state-inspection call with no configuration options.

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?

'Returns the current toolkit state' names a specific verb and resource, then enumerates the exact content delivered (installed MCPs, connection status, accounts per MCP, catalog tool counts). This clearly distinguishes it from siblings like connect, authenticate, or report_bug — it's an inspection/summary tool, not an action tool.

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 what information is returned but never states when to use this tool versus alternatives. It doesn't reference siblings like connect or authenticate, nor does it mention typical usage scenarios (e.g., checking readiness before connecting, verifying installed MCPs). The usage context is inferable but not explicit — adequate, not helpful.

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