IBAMA: Certidão de Embargos (Nada Consta)

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

Annotations indicate idempotent and non-destructive, which the description aligns with. It adds valuable context about session vs permanent behavior (config-based vs pasted token) and the non-expiring nature of config-based auth. This goes beyond what annotations provide, making the side effects clear.

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, but they are dense and packed with essential info. The first sentence sets the audience and purpose, the second details the two usage patterns. It avoids fluff but could be slightly more streamlined for readability.

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 output schema and a single optional parameter, the description covers what the tool does, how to use it, and the two distinct use cases (permanent vs session). It doesn't explain return format, but that's not required given the simplicity and annotations.

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% coverage (token has no description), but the description explains that 'token' is the JWT to paste for session login, and that omitting it yields a login link. This fully compensates for the schema gap, clarifying both the parameter and the 'no arg' 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?

Description clearly states it's for authentication ('log in in the browser, copy the access token') and explains the two modes: getting a login link (no args) or session login with a JWT token. It distinguishes from siblings like 'connect' and 'marketplace' by focusing specifically on authentication for IDE agents.

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 usage instructions: either no args to get a link, or with a token for session login. It also recommends the config-based permanent approach as best practice but doesn't say when not to use it. It gives clear context but lacks explicit exclusions or alternatives beyond the tool's own modes.

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, so the description does not repeat these. It adds value by describing the exact response shape (authenticated, pending, connect_url) and the conditional behavior when credentials are missing, providing behavioral detail beyond the annotations.

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

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

Two concise sentences that front-load the purpose and then provide conditional outcomes. No redundant phrases or filler; every sentence 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 zero-parameter, read-only status tool, the description fully covers the return behavior in both normal and error-prone scenarios (missing credentials). Since there is no output schema, this description is essential and sufficient.

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

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

There are zero parameters and the input schema is empty, so schema coverage is 100% by default. The description does not need to elaborate on parameters, and the baseline for zero-parameter tools is 4. No contradiction.

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, with specific conditions for when providers are connected versus when credentials are missing. It distinguishes from siblings like authenticate by focusing on status inspection rather than initiation.

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 and provides context on what results to expect, but does not explicitly contrast with alternatives or state when not to use it. Given the read-only nature and sibling tools, the intended use is clear enough without exclusions.

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?

Beyond the annotations (read-only, idempotent, non-destructive), the description discloses extra behavioral traits: it requires pre-paid payment, does not need platform credentials, and clarifies data handling under LGPD (client as controller, non-confidential data). This goes well beyond the annotation info.

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 short and to the point, but it contains some redundancy (repeats 'official source' and 'not confidential' multiple times). It is structured as a flowing paragraph without bullet points, but it is not overly verbose. Acceptable but could be tighter.

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 provides useful context about payment, data privacy, and the official nature of the data. However, it does not explain the expected output or how the parameters are used (e.g., whether CPF or CNPJ must be provided). Given its simplicity, it is moderately complete but leaves important gaps for the agent.

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 lists two parameters (cpf and cnpj) but provides no descriptions. The description does not explain their meaning, usage, or whether they are mutually exclusive or both required. With schema coverage at 0%, the description fails to compensate, so this dimension is very weak.

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: it performs a consulta (query) for IBAMA's embargo certificate (Certidão de Embargos), specifying the resource and action. It also distinguishes itself from sibling tools (authenticate, marketplace, etc.) by focusing on this specific certificate query.

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 context on when to use the tool (for consulting embargo certificates from official Brazilian sources) and mentions operational details (pre-paid credits, no platform credentials). However, it does not explicitly compare with alternative tools or state exact conditions for use, but given the specific nature, the guidance is adequate.

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?

Beyond the annotations, the description discloses substantial behavioral details: invoke performs a one-off install that does not bloat the toolkit, writes require workspace owner/admin, search/describe flag installed_in_toolkit vs installed_in_workspace, and publish_prompt creates a shareable link that opens without login. It also covers edge-case behavior for missing credentials and empty wallets. None of this contradicts the annotations, and it greatly exceeds what readOnlyHint/destructiveHint/idempotentHint alone convey.

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 packed and organized with labeled sections: definition, core flow, KEY behavior, install-vs-invoke guidance, auxiliary actions, permissions, and prompt library. Every sentence adds useful information for a tool with 14 actions, though a few returns/sub-lists could be tightened or separated for easier scanning. It is efficient given the tool's complexity.

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 high complexity (23 params, 14 actions, two sub-domains, no output schema), the description is remarkably complete. It explains the discovery-to-invocation lifecycle, handles credential/payment edge cases, covers permissions, lists all auxiliary actions, and fully introduces the prompt library with its core actions and link behavior. The only minor gaps are fine-grained output shapes, but the description already exceeds what is typically needed for correct tool selection and invocation.

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

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

With 23 parameters and 0% schema description coverage, the description carries the full burden and does add meaning: it explains action values, mcp_id/tool_id/arguments via the search/describe/invoke flow, and prompt_vars/prompt_slug via the prompt-library behavior. However, many parameters like limit, query, immediate, tier_slug, cancel_reason, prompt_targets, and report_context are not explained, so the parameter guidance is strong for the core flow but incomplete for peripheral actions.

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 by defining the tool as “the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,” which clearly establishes its role. It then maps the core flow (search → describe → invoke) and enumerates the prompt-library sub-domain, making the broad scope unmistakable. It also distinguishes itself from siblings by covering actions like report_bug and connect-related behavior, so it is not confused with the standalone 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 description gives explicit decision guidance: use invoke for one-off runs even when an MCP is not installed, and use install only to make an MCP permanent in the active toolkit. It also explains when to use list_tools, subscribe/cancel, report_bug, and request_mcp, and preemptively describes the auth/payment retry flow after invoke returns a connect or checkout link. This is exemplary when-to-use guidance for a multi-action router tool.

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 a hint about including conversation for reproduction but does little beyond annotations. Annotations already indicate idempotent and non-read-only behavior. No contradiction, but limited additional insight into side effects or requirements.

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 concise sentences, front-loaded with purpose. Every word earns its place, no fluff or 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 simple schema (3 params, 1 required, no output schema) and the clear purpose, the description is adequate. It covers the key param (conversation) and context. The 'context' param is missing an explanation, but the overall tool is straightforward enough that the description suffices.

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 adds meaning only for the 'conversation' parameter by specifying its use for reproduction. The 'context' parameter is left unexplained, and 'message' is self-evident. Since schema coverage is 0%, the description partially compensates but not fully.

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 reports bugs, missing features, or feedback, which is specific and distinct from siblings like 'marketplace' or 'toolkit_info'. The verb 'report' and resource 'bug/missing feature/feedback' make the purpose 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?

It provides explicit guidance to include the conversation array for reproduction, which is useful when reporting issues. However, it does not explicitly mention when not to use the tool or alternative tools, though siblings are clearly different in 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, so the safety profile is known. The description adds the specific focus on platform and adapter versions but no additional behavioral caveats. 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 a single, front-loaded sentence that states the purpose with no filler or redundant wording. Every word contributes to understanding the 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 its simplicity — no parameters, no output schema, and a clear informational purpose — the description fully covers what an agent needs to select and invoke this tool correctly.

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

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

The tool has zero parameters, so there is no parameter meaning for the description to add. Per the baseline for zero-parameter tools, a score of 4 is appropriate; the description does not need to compensate for 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 uses a precise verb ('Show') and a specific resource ('current MCP platform and adapter versions'). This clearly distinguishes it from sibling tools like authenticate or connect, which suggest different actions.

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: use when the current platform and adapter versions are needed. It does not explicitly state exclusions or name alternatives, but for a zero-parameter informational tool, this is reasonable and sufficiently scoped.

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, setting a high baseline. The description goes beyond by disclosing exactly what information is returned (installed MCPs, connection status, accounts, tool counts), which is rich behavioral context. It adds value by detailing the output structure without any 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, well-structured sentence that front-loads the most critical information ('Returns the current toolkit state') before enumerating the specific components. Every phrase earns its place, with no redundant words or unnecessary detail. It is a model of conciseness.

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 info tool, the description is fully complete: it explains what the tool returns and covers all key aspects of the toolkit state. There is no output schema to align with, and the annotations handle safety and idempotency, so nothing critical is missing.

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 in the input schema, there is nothing to explain about parameter semantics. According to the rubric, a score of 4 is the baseline when there are no parameters, as the description does not need to compensate for any schema gaps. The description appropriately focuses on return behavior instead.

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 starts with the specific verb 'Returns' and clearly defines the resource: 'the current toolkit state' followed by concrete details (installed MCPs, connection status, connected accounts, catalog tool counts). This level of specificity clearly differentiates the tool from siblings like 'show_version' or 'authenticate', making the purpose unmistakable.

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 is so self-explanatory that usage is implied—any agent needing an overview of the toolkit would use this tool. However, the description does not explicitly state when to use it versus alternatives, nor does it mention any exclusions or conditional logic. It relies on the reader to infer usage from the clarity of purpose, which aligns with a 3 (implied usage).

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