Prefeitura GO Campos Verdes: Certidão Negativa de Débitos

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

Annotations already indicate idempotent, non-destructive, and non-read-only. The description adds context about the login flow, session vs permanent connections, and the option to configure a header. This goes beyond annotations and provides useful behavioral detail 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 compact yet covers all essential info, using distinct segments for flow, best practice, and fallback. Every sentence adds value, and the structure is logical with front-loaded purpose.

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 tool with one optional parameter and no output schema, the description covers all usage modes, prerequisites (browser login, token acquisition), and configuration options. It is complete enough for an agent to invoke 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?

Schema coverage is 0%, so the description must fully explain the token parameter. It does: it clarifies that token is a JWT pasted for session login, and that omitting it returns a link. This is comprehensive and helpful, exceeding the baseline.

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 handles authentication for MCP.AI IDE agents, describing the login flow and token usage. It is specific about the action (authenticate) and the resource, but it does not explicitly distinguish from sibling tools like 'connect' or 'marketplace', so it falls slightly short of a 5.

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 usage context: it explains when to call with no args to get a link, when to pass a token for session-only login, and recommends the config header for a permanent connection. It gives explicit scenarios but does not mention exclusions or alternative tools, so it merits a 4.

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 false. The description adds meaningful behavioral detail beyond annotations by explaining the exact return conditions: authenticated:true with empty pending[] versus connect_url and per-install URLs when credentials are missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the primary purpose, and every clause adds meaningful detail about conditional return values. No filler or repetition of annotation data.

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 explains the return behavior in both relevant states. Even without an output schema, the agent understands what to expect: authenticated:true with empty pending[] or connect_url and per-install URLs.

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 coverage is 100%, so the schema fully documents the input surface. Per the baseline for 0-param tools, the description does not need to add parameter detail; it correctly focuses on output 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 opens with a specific verb and resource: 'Returns connection status and URLs.' This clearly identifies the tool's function and distinguishes it from siblings like authenticate, which performs authentication rather than reporting 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 provides clear conditional context for when the tool returns different results (all providers connected vs. missing credentials). It implies the tool is used to check connection status, though it does not explicitly name alternatives or state when not 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 include readOnlyHint false, openWorldHint true, idempotentHint false, destructiveHint false. The description adds substantial behavioral context: invoke works even if MCP is not installed, returns connect/checkout links on credential/payment requirements, and notes that writes require admin. This is beyond annotations and does not contradict them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph over 200 words. It contains valuable information but lacks structure (e.g., bullet points or sections). While the complexity justifies length, it could be more concise and organized 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?

Given 23 parameters and no output schema, the description covers the core workflows and even edge cases (connect/checkout links, permissions). It does not explain all actions in depth (e.g., resume, cancel_reason details) but provides enough for an agent to make correct choices. The lack of output schema details is partially mitigated by describing expected links.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries full burden. It explains the core parameters (action, mcp_id, tool_id, arguments) within the flow but leaves many others (e.g., limit, query, cancel_reason, prompt_* fields) unexplained. While the high-level flow helps infer some usage, it does not systematically document each parameter, leaving gaps.

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, covering catalog discovery and execution of MCPs. It explicitly lists the core flow (search → describe → invoke) and differentiates from sibling tools like authenticate and toolkit_info by describing its unique multi-action nature. The verb 'marketplace' plus the explanation of its capability to run tools makes it unambiguous.

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 explicit guidance on when to use invoke vs. install, when to use search vs. describe, and clarifies that writes require workspace owner/admin. It also mentions alternatives implicitly for prompt library actions. This exceeds typical usage guidance by offering decision rules and prerequisite conditions.

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 value beyond the annotations: it discloses the payment model (pay per consultation), the data source's official nature, and the LGPD compliance responsibility. These are not in the annotations, so the description is adding useful behavioral context. It aligns with readOnlyHint=true.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the primary purpose. It includes some legal/administrative details that are relevant but could be trimmed. Overall, it is reasonably concise 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?

For a simple read-only tool, the description provides good context about payment and data governance. However, it lacks essential detail about the parameters (CPF/CNPJ) and does not describe what the output looks like (though no output schema is provided, the agent still needs to know what the response contains). Missing parameter guidance is a notable 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 schema has 0% coverage for parameters (cpf and cnpj), and the description does not compensate by explaining their purpose or that one of them is required. The description never mentions the parameters, so an agent cannot determine how to populate them correctly.

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 specifies the tool's purpose: querying a Negative Debt Certificate (CND) from a specific municipality (Campos Verdes, GO). The verb 'consultar' and resource are explicit. It is distinguishable from the generic sibling tools like 'authenticate' or '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?

It provides some context (official source, payment per consultation), but does not explicitly state when to use this tool versus alternatives, nor does it mention the required parameter usage (CPF/CNPJ). It does not give exclusions or prerequisites beyond mentioning it is hosted on the platform.

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 include idempotentHint=true and destructiveHint=false, which the description does not contradict. The description adds useful behavioral context by specifying that the conversation array should be included for reproduction, which is beyond what annotations convey. No return format or side effects are mentioned, but the annotations cover the safety profile adequately.

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 long and front-loaded with the core purpose. Every word earns its place, and it avoids fluff. It is well-structured for quick reading.

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 tool with 3 parameters, no output schema, and no nested objects, the description covers purpose, usage, and the key parameter needed for reproduction. It doesn't explain all parameters or return behavior, but given the tool's simplicity, it is reasonably complete. The missing param details are the main 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?

Schema description coverage is 0%, so the description must compensate. It explicitly mentions the 'conversation' parameter and its purpose ('for reproduction'), which provides some semantic meaning. However, it doesn't clarify the 'message' (though required, it's self-explanatory) or 'context' parameters. The description adds value for conversation but leaves two parameters without additional explanation.

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: 'Report a bug, missing feature, or send feedback.' This is a specific verb+resource pattern (report, missing feature, feedback) and effectively differentiates from sibling tools like authenticate or marketplace, which have unrelated purposes.

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 usage context by instructing the user to 'Include the conversation array with recent messages for reproduction.' This gives a practical guideline on what to provide. However, it lacks explicit when-not-to-use guidance or alternative tool references, so it earns a 4 rather than 5.

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 indicate readOnlyHint: true, idempotentHint: true, and destructiveHint: false, so the agent safely knows this is a read-only, side-effect-free operation. The description adds a modest behavioral detail: the versions are 'current' rather than cached, and it names platform/adapter as the scope. However, it stops short of describing response format, possible variants, or failure behavior, so added transparency is limited.

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 short, front-loaded sentence: 'Show the current MCP platform and adapter versions.' Every word is useful, there is no fluff, and the action and target are immediately visible.

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 that the tool has zero parameters, strong annotations covering side effects and idempotence, and no output schema, the description is sufficiently complete for an agent to select and invoke the tool. It names the exact resource being reported and conveys that no arguments are expected. There is no missing behavioral information that would affect a call decision.

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 is empty and has 0 parameters, so schema coverage is trivially 100%. Every schema property is exhausted; the description correctly does not invent parameters. Per the rubric, a 0-parameter tool gets a baseline of 4 because there is nothing to explain.

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' with a clear resource: current MCP platform and adapter versions. It is unambiguous and distinct from the sibling tools, which involve authentication, marketplace, or consultant consultations. Even with the generic title 'Show Version', the body clarifies exactly what the tool reports.

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 should be used when checking the current platform/adapter versions, but it gives no explicit when-to-use vs. alternative guidance. With sibling tools like toolkit_info and marketplace present, the description does not state why show_version should be preferred over these. The use case is clear enough from the phrase 'Show the current...', but no exclusions or prerequisites are 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?

Annotations already establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description builds on this by detailing what the read encompasses (MCPs, statuses, accounts, tool counts), adding value beyond the structured safety annotations. It stops short of disclosing response shape or potential for stale data, but for a state-inspection tool this is solid. No contradictions with 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?

A single, efficiently structured sentence that front-loads the core purpose ('Returns the current toolkit state') before enumerating the details. Every element earns its place, with zero filler. The em-dash structure cleanly separates the headline from the enumeration of what state is included.

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 inspection tool with rich annotations and no output schema, the description carries the burden of explaining the return value, which it does by listing the four categories of state returned. It could add why this matters (e.g., connection troubleshooting) but is otherwise complete for the tool's modest complexity.

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 zero parameters, the tool requires no explanation beyond what's provided. The schema is trivially 100% covered since no parameters exist. Per calibration, a zero-param tool gets a baseline of 4, and the description appropriately focuses its energy on output semantics instead of inputs.

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 begins with a specific verb+resource combination ('Returns the current toolkit state') and enumerates exactly what that includes: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly differentiates it from siblings like `show_version` which would cover a narrower or different status surface, even if not explicitly named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied rather than explicit. The read-only inspection purpose is obvious from the description, so an agent would naturally reach for it when needing toolkit state. However, there's no explicit when-to-use or when-not-to-use guidance distinguishing it from adjacent tools like `show_version` or `pref_go_campos_verdes_cnd_consultar`.

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