Regularidade FGTS (CRF)

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

Annotations already indicate idempotentHint=true and readOnlyHint=false. The description adds valuable context about the two authentication flows (permanent vs session-only), the browser interaction requirement, and the use of a bearer token. It does not describe the response or side effects beyond login, but for a simple auth tool this is adequate.

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 three sentences, information-dense without fluff. It could be better structured with bullet points, but it remains readable and each clause provides essential information about how to authenticate.

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 one-parameter tool with no output schema, the description covers the main usage scenarios: obtaining a link and using a token. It also explains the permanent config approach, which is useful context for agents. It does not specify the exact response or error behaviors, but these are not critical for a straightforward auth action.

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% and the 'token' parameter has no description. The description compensates by explaining that token should be a JWT and that it is optional (calling with no args yields a link). This adds clear meaning beyond the bare schema type of string.

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 an authentication mechanism for IDE agents, specifying the verb 'log in' and the resource (MCP.AI access). It distinguishes between permanent (config header) and session-only (token paste) authentication, making the tool's 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?

The description provides explicit usage instructions: call with no args to get a login link, or call with a JWT token for session login. It also recommends adding the token to the server config for a permanent connection. However, it does not explicitly compare with sibling tools like 'connect' to state when one should be used over the other.

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 read-only nature is known. The description adds valuable behavioral context beyond annotations: it specifies conditional outputs (authenticated:true and empty pending[] when connected, or connect_url when credentials are missing). This helps the agent predict response variations without being redundant 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 two sentences, front-loaded with the main purpose, and every sentence adds meaningful detail. No fluff or repetition of annotations.

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 no-parameter status tool with no output schema, so the description carries the full burden for return-value understanding. It covers the main states (all connected vs missing credentials) and includes the key fields (authenticated, pending[], connect_url). However, it doesn't enumerate all possible response fields or the structure of 'per-install URLs', but given the tool's low complexity, this is nearly 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 zero parameters, the schema covers everything (100% coverage). The description does not need to explain parameter syntax or values. Baseline for 0 params is 4, and the description appropriately focuses on return behavior rather than nonexistent 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, using a specific verb ('returns') and resource. It distinguishes itself from siblings like 'authenticate' by focusing on status, and the conditional details about authenticated:true and connect_url provide concrete scope.

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 check tool, usable when you need to know connection state or get URLs. However, it does not explicitly mention when not to use it or how it relates to alternative tools like 'authenticate'. No exclusions or direct comparisons are provided, only implicit 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?

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses important behavioral traits: no credentials, pay-per-use with prepaid credit, and that the data is public non-confidential information with LGPD compliance. This adds substantial context about access, cost, and legal use, exceeding what annotations 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 three sentences: the first states the core purpose, the second explains access/payment, and the third covers legal/LGPD. While concise, the third sentence could be seen as secondary but still relevant. Overall it is well-structured and front-loaded.

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 two parameters and no output schema, the description covers purpose, access model, payment, and legal compliance, but omits the meaning of the 'completo' parameter and does not describe the return format. The gaps are notable but not fatal given the tool's simplicity.

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 (Cnpj, completo) with no descriptions, and the description only references 'CNPJ' without explaining the 'completo' boolean. Schema coverage is 0%, so the description fails to clarify the optional parameter's meaning, leaving a critical gap.

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

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

The description clearly states the tool's function: 'Emite o Certificado de Regularidade do FGTS (CRF) de um empregador a partir do CNPJ.' This is a specific verb, resource, and input. It distinguishes itself from unrelated siblings (authenticate, connect, marketplace, etc.) by being the only tool for FGTS certificate issuance.

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 operational context: hosted by the platform, no credentials required, prepaid credit per query, and it accesses public information. It does not explicitly mention alternatives or exclusions, but the context is sufficient for an agent to decide when to use this 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?

Annotations already indicate readOnlyHint=false, openWorldHint=true, and destructiveHint=false. The description adds substantial behavioral context beyond those flags: writes require workspace owner/admin, invoke returns a connect link when credentials are missing, paid tools return a checkout/top-up link when the wallet is empty, and one-off invoke does not install or bloat the tool list. No contradiction with annotations.

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

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

The description is long but front-loaded with the core flow before alternative actions, and every sentence conveys useful information. It is, however, a dense single paragraph that mixes catalog navigation, billing, permissions, and prompt-library behavior, with one stray Portuguese word ('pontualmente'). It would be more scannable with bullets, but it is not wastefully verbose.

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 23 parameters, no output schema, and complex business logic, the description covers the main workflows, auth/payment edge cases, permission requirements, and prompt-library operations. It is not fully complete—return-value shapes, search pagination, and error behavior are absent, and many parameters remain unexplained—but it provides enough context to use the primary path effectively.

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% with 23 parameters, so the description must compensate. It explains the role of action values and explicitly mentions tool_id, mcp_id, and prompt variables/slugs. However, many parameters (limit, immediate, tier_slug, conversation, prompt_tool, prompt_targets, prompt_category, request_details, arguments, etc.) are not explained, leaving the agent to infer their meaning from names 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 clearly identifies the tool as 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them'. It specifies the core verbs (search, describe, invoke, install) and explicitly mentions report_bug as an action, which distinguishes it from the sibling tool of the same name. The purpose is unambiguous despite the broad scope.

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 when-to-use guidance with named alternatives: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use', and explains when to use search/describe, list_tools, subscribe/cancel, request_mcp, and the prompt-library actions. It even includes concrete triggering examples like 'find an MCP that does X' and 'consulta um CPF'.

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 the tool as idempotent and non-destructive. The description adds a behavioral requirement (including the conversation array for reproduction) but does not disclose other traits like authentication needs or side effects. Since annotations cover the basic safety profile, a score of 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 concise, using only two short sentences that both provide value. It is front-loaded with the core action and includes a key usage hint without fluff or repetition.

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 and no output schema, the description gives enough context to understand the overall purpose and the importance of the conversation array. However, it leaves the message and context parameters unexplained, which creates a gap in completeness for a tool that requires a message.

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%, placing the burden on the description to explain parameters. The description only explains the 'conversation' parameter ('Include the conversation array with recent messages for reproduction') and leaves the required 'message' parameter and the optional 'context' parameter undefined. This is insufficient for an agent to know precisely what to provide in those 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 tool's function with specific verbs and resources: 'Report a bug, missing feature, or send feedback.' It is unambiguous and distinct from sibling tools like authenticate or connect, which serve entirely 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 conveys the clear context for use—whenever a bug, missing feature, or feedback needs to be communicated. It also provides an instruction ('Include the conversation array with recent messages for reproduction') that helps the agent use the tool effectively. However, it does not explicitly mention alternatives or exclusion scenarios, so it lacks full sibling differentiation.

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 clear. The description adds the context that it shows 'current' versions and covers both platform and adapter components, which is helpful but not extensive. No contradictions exist.

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, compact sentence that conveys the complete purpose without any filler. Every word contributes meaning, making it exemplary in 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 simple, parameterless, read-only version tool, the description covers the purpose and is backed by strong annotations. It does not explicitly describe the return format, but for 'show version' tools the response is usually obvious. The description is sufficiently complete for the tool's simplicity.

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 the input schema fully reflects this. The description adds no parameter details because none are needed. Baseline of 4 is appropriate for a parameterless tool.

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 the specific verb 'Show' and names the exact resources: 'MCP platform and adapter versions.' It clearly distinguishes this tool from siblings like authenticate, connect, and marketplace, which deal with different concerns.

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?

While no explicit 'use when' or alternative guidance is provided, the tool's purpose is self-evident and no sibling directly competes with it. The description implies using this tool whenever version information is needed, which is sufficient for a trivial version display 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds behavioral context by specifying what information is returned, going beyond the annotations without contradicting 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?

A single sentence that front-loads the action ('Returns'), enumerates the key output categories, and contains no wasted words. Every phrase adds value.

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 no-parameter, read-only info tool, the description completely captures what an agent needs to know to decide to call it. The lack of an output schema is compensated by a clear list of the returned information groups.

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 no parameters, so the baseline is 4. The description adds no parameter details, but none are needed; the absence of schema properties makes the tool self-explanatory.

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 ('Returns') and clearly defines the resource ('current toolkit state') with enumerated details (installed MCPs, connection status, accounts, catalog tool count). This distinguishes it from sibling tools like show_version, which likely focuses on version 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?

While no explicit alternatives are named, the description clearly implies this tool is for inspecting the current toolkit state, which is distinct from state-changing siblings like connect and authenticate. The absence of exclusions is acceptable given the uniqueness of its purpose.

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