SICONFI: Declaração Fiscal

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

The annotations indicate idempotency and non-destructive behavior, but the description only partially discloses side effects. It mentions session-only login, implying temporary state, but does not clarify return values for token-based calls or potential errors, leaving some behavioral 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 verbose and runs multiple instructions together without clear separation, mixing user guidance with tool invocation details. It could be streamlined to improve readability and reduce cognitive load.

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?

While the description covers the main usage scenarios, it lacks explicit details about return values for successful token authentication and does not address error handling or output format. Given the absence of an output schema, this omission reduces completeness for an authentication tool.

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

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

The single parameter 'token' is clearly described as the access token (JWT) to be pasted, with an explanation that it is optional and that omitting it returns a login link. This fully compensates for the lack of schema-level description.

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 is for authentication, guiding the user to log in via browser and copy an access token. It differentiates from sibling tools like 'connect' and 'marketplace' by focusing specifically on login and token management.

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 explicit usage instructions, including when to call with a token and when to call with no arguments to obtain a link. It also recommends a preferred method (adding to config) and notes a session-only alternative, giving actionable 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 behavioral details beyond annotations by specifying the return values in different conditions (all providers connected vs missing credentials). It does not contradict the readOnlyHint or other 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 two sentences, front-loaded with the main purpose, and provides necessary detail without excess. 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?

The tool is simple with no parameters and no output schema, but the description covers the two distinct outcomes. It could be more explicit about the exact structure of the URLs or the meaning of 'per-install URLs', but it gives sufficient context for an agent to understand the tool's 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?

No parameters exist, so baseline is 4 per rubric. The description appropriately explains the tool's behavior without needing to document parameters.

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 behavior for connected vs missing credentials. It distinguishes from siblings like authenticate (for authentication) by focusing on connection state.

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 but does not explicitly state when to use it vs alternatives, nor does it mention sibling tools or give examples of when not to use.

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 annotations are minimal (all false/defaults except openWorldHint), so the description carries full burden — and it delivers. It discloses side effects (invoke runs tools one-off 'without adding the MCP to the toolkit'), auth requirements (connect link), payment edge cases (checkout/top-up link 'then you retry'), and permission requirements ('Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin'). This is precisely the behavioral context annotations don't 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?

Every sentence carries substantive information and the description correctly front-loads the most important info (core purpose and flow) before edge cases and permissions. However, it is rendered as one massive wall of text with no paragraph breaks, punctuation awkwardly mixed between the English/Portuguese content, and no scannable structure despite covering ~15 distinct behaviors. Each sentence earns its place, but the lack of organization hurts scannability.

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 14-action dispatcher with no output schema and minimal annotations, the description is remarkably thorough: it covers the discovery flow, execution flow, not-installed behavior, auth/payment handoffs, install-vs-invoke semantics, billing operations, bug reporting, new-MCP requests, permissions, and all three prompt-library functions. Minor gaps exist (e.g., cancel/resume specifics, what list_tools returns), and it reads as slightly overstuffed, but for the scale of the tool it is impressively complete.

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% schema description coverage across 23 parameters, the description bears the full explanatory burden. It does cover roughly 15 of 23 parameters implicitly through the action narrative (query, mcp_id, tool_id, arguments, prompt_slug, prompt_vars, prompt_body, etc.) and explains enums like action's sub-commands. However, it leaves several parameters entirely unexplained (limit, immediate, tier_slug, conversation, request_name, prompt_targets, cancel_comment, report_context, request_details, prompt_category). Solid effort given the scale, but not complete 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 opens with a specific, unambiguous statement: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then articulates a clear core flow (search → describe → invoke) and differentiates the prompt-library sub-functionality. Though it covers many actions, each is tied to a concrete verb+resource, making the tool's purpose unmistakable despite being a multi-action dispatcher.

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?

Exceptionally strong when-to-use guidance. It names concrete trigger queries ('find an MCP that does X', 'consulta um CPF'), explicitly contrasts invoke vs. install ('Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use'), and enumerates sibling-style alternatives (list_tools, report_bug, request_mcp, search_prompts). It even handles edge cases for auth/billing links and retry semantics, going well beyond basic 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?

Annotations already indicate the tool is idempotent and non-destructive but not read-only. The description adds the behavioral expectation that the conversation array should be submitted for reproduction, which is some extra context. It does not discuss side effects, where the report goes, or whether confirmation is returned, but the annotations cover the basic safety profile.

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 only two sentences and front-loads the core purpose before giving the one essential usage note. Every sentence contributes meaningful information with no wasted 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?

This is a simple reporting tool with a small schema and no output schema, so the description covers the main purpose and the key usage requirement (include conversation). The only meaningful gap is the lack of clarification for the 'context' parameter, but overall the tool is sufficiently understandable for 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?

Schema description coverage is 0%, and the description only partially compensates by mentioning 'conversation array with recent messages'. It does not explain 'message' or 'context' as specific parameters, leaving the agent to infer their meaning from the schema alone.

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 ('Report') and clearly identifies the resource scope: bugs, missing features, and feedback. This makes its purpose immediately distinguishable from the sibling tools, none of which are feedback-related.

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 clear practical guidance ('Include the conversation array with recent messages for reproduction') and defines the appropriate context for the tool: reporting bugs, missing features, or sending feedback. It does not explicitly state when not to use it or name alternatives, but the use case is unmistakable.

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, which covers the safety profile. The description adds the behavioral clarification that it returns version information for both the MCP platform and adapters, which is useful given the lack of an output schema.

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 immediately communicates the tool's purpose with no filler or redundancy. It earns its place by specifying both what is shown and the scope (MCP platform and adapter).

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 version-inspection tool, the description is sufficiently complete. It states what the tool returns in terms of domain-relevant categories and does not require details about parameters or complex side effects to be usable.

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 takes zero parameters, so no additional parameter semantics are needed. The schema coverage is effectively complete at 100%, and the description matches the no-parameter expectation. Per the rubric, zero parameters warrants a baseline of 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a clear verb ('Show') plus the specific resource ('current MCP platform and adapter versions'), making the tool's purpose immediately obvious. It also distinguishes itself from sibling tools like toolkit_info by specifying platform and adapter versions rather than general toolkit info.

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

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

The description clearly implies when to use this tool—whenever version information is needed—but it does not provide explicit when-to-use or when-not-to-use guidance. No alternatives are named, even though sibling tools like toolkit_info could plausibly overlap in functionality.

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 declare readOnlyHint=true and idempotentHint=true, which the description complements by disclosing payment requirements (prepaid credit), legal responsibilities (LGPD), and data nature (public, not confidential). This adds value beyond annotations without contradiction, though it does not describe the return format or pagination.

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, covering purpose, payment, data nature, and legal responsibility in four sentences. It is front-loaded with the core purpose, and every sentence adds meaningful context, though the legal and payment details could be more compact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 7 parameters, no output schema, and no parameter descriptions in the schema or description, the tool is under-specified. The description provides external context (payment, legal) but fails to explain how to construct a valid query, what the parameters mean, or what the response contains. For a tool with this complexity, it is not complete enough for an agent to use 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 description coverage is 0%, and the description does not explain any of the 7 parameters (esfera, ente, poder, orgao, exercicio, uf, titulo). The parameter names are somewhat self-explanatory (e.g., 'exercicio' as fiscal year), but the description fails to compensate for the complete lack of schema descriptions, leaving users to guess the meaning of required fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the purpose: 'consulta em fonte oficial' (query from official source) of 'Declaração Fiscal' (tax declaration) from SICONFI. It identifies a specific verb (consultar) and resource (SICONFI fiscal declaration), which distinguishes it from sibling tools that are unrelated (authenticate, connect, etc.).

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 usage: hosted by the platform, no platform credentials needed, pay per query with prepaid credit, and data is public (not confidential). It implies when to use (to consult official Brazilian fiscal data) but does not explicitly state when not to use or mention alternatives, though none exist among siblings.

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, covering the safety profile. The description adds the scope of information returned but nothing about side effects or edge cases. Given the annotations cover the main behavioral traits, the description adds value with the state summary but doesn't add deeper context like connection failures or refresh behavior.

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

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

The description is a single, well-structured sentence that lists exactly what the tool returns. No fluff or redundancy. It front-loads the verb 'Returns' and the resource 'current toolkit state'.

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 tool with clear annotations, the description is sufficiently complete. It specifies the major data categories returned. Without an output schema, a bit more detail on the exact format could be useful, but the description covers the essentials.

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 the description doesn't need to explain parameter semantics. The baseline for zero params is 4, and the description appropriately describes what the output contains, which satisfies the intent.

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 the current toolkit state, listing specific categories: installed MCPs, connection status, accounts, and catalog tool counts. This distinguishes it from sibling tools like authenticate, connect, marketplace, and report_bug, which have obviously different 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 implies this is a status/inspection tool, appropriate when needing an overview of the toolkit's current state. It doesn't explicitly mention when not to use it, but the clarity of its purpose relative to siblings provides good context for selection.

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