ANTT: Produtos Perigosos

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

It discloses that queries are paid (prepaid credits), data is not confidential, and the client is responsible for LGPD compliance. This aligns with the read-only annotation, although side effects beyond cost are not explicitly described.

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, combining functional details with billing, legal, and data privacy statements in a single block. It could be more concise and better structured for quick comprehension.

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 context about the official source and legal aspects but fails to mention what output the query returns or how the parameters relate to the query. It is incomplete for a tool with only two parameters and no output schema.

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 parameters 'placa' and 'tipo_certificado' are not explained at all in the description. Their roles in the query are unclear, leaving users to infer their meaning from the tool context.

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 queries dangerous products information from ANTT, an official Brazilian source. The core purpose is explicit, though the description also includes peripheral billing and legal details that slightly dilute the focus.

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 mentions that the tool requires prepaid credits and no platform credentials, but it does not provide guidance on when to use this tool versus alternatives or specific conditions for invocation.

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 transparently explains that calling with no args yields a link, calling with a token performs a session-only login, and the recommended approach is a config header for a permanent, non-expiring connection. This adds meaningful behavioral detail beyond the structured annotations (idempotent, non-destructive) 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?

The description delivers a lot of relevant guidance in three sentences, with the key actions clearly separated. It is slightly verbose due to the 'MCP.AI for IDE agents' preface and the long config recommendation, but every sentence earns its place and the reading is efficient.

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 there is no output schema and only one optional parameter, the description adequately covers what the tool does and how to invoke it. It lacks an explicit statement of return values beyond 'get the link,' but the tool is simple enough that this omission is acceptable, yet a clear description of success/failure would push it further.

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 only parameter, 'token', is not described in the schema, but the description fully compensates: it explains that the token is a JWT, should be pasted, and that calling with no arguments is also valid. This clarifies both the semantic and the optionality of the parameter.

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 indicates the tool is for authenticating to the MCP server: the agent can log in via browser, get an access token, and pass it as a token or obtain a link. However, it mixes product/brand context ('MCP.AI for IDE agents') and top-level instructions that are not a crisp verb+resource statement, slightly reducing clarity.

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 direction: 'Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.' This clearly explains the two main call modes, the recommended alternative, and the context for each.

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 read-only, idempotent, and non-destructive hints. The description adds value by detailing the response structure (authenticated:true, empty pending[], or connect_urls), which goes beyond the annotation hints. It does not contradict annotations and provides helpful behavioral context.

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, with two sentences that front-load the primary purpose and then explain state-dependent outputs. Every word earns its place, with 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?

The tool is simple (no parameters, no output schema), and the description adequately covers the return values in both relevant states. It provides sufficient context for an agent to understand what to expect, and there are no additional complex behaviors that need explanation.

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 baseline for parameter semantics is 3. The description adds no parameter-specific information because there are none to document; it doesn't need to compensate.

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 a specific verb and resource. It distinguishes from siblings like authenticate (which likely initiates connections) and show_version (version info) by focusing on 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 implies usage context: checking connection status. It explains the two possible outcomes (all connected vs missing credentials) which clarifies when it's useful. However, it does not explicitly mention alternatives or when not to use it, but the context is clear enough.

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?

Even with annotations present, the description adds significant behavioral context: invoke runs uninstalled MCPs one-off without bloating the tool list, paid tools return checkout/top-up links, and writes require workspace owner/admin. These details go well beyond the sparse annotation hints and are not contradicted by 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 dense yet efficient, with every clause adding meaningful information: the core flow, invoke edge cases, install guidance, auth requirements, and prompt library. It is front-loaded with the primary purpose and uses 'KEY:' to emphasize the most important behavior.

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 14 actions and 23 optional parameters, the description is unusually thorough, covering billing, auth, install semantics, one-off invocation, and prompt publishing. It still omits exact per-action parameter mappings for actions like resume, subscribe/cancel details, and report_bug, leaving minor ambiguity for an 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?

With 0% schema coverage, the description carries the burden of explaining parameters. It does explain the key `action` values and major params like `query`, `mcp_id`, `tool_id`, `arguments`, `prompt_vars`, and `prompt_slug`. However, several params remain unexplained (`resume`, `immediate`, `tier_slug`, `cancel_reason`, `report_context`, etc.), leaving some 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 opens with 'official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' giving a clear verb+resource definition. It also concretely lays out the search→describe→invoke flow and the prompt library, making the tool's purpose unmistakable and distinct from siblings.

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 explicitly frames the core flow: action=search discovers MCPs, describe returns a profile, invoke runs the tool. It also gives direct usage guidance such as 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT,' clearly separating when to use which action.

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 idempotentHint=true and destructiveHint=false, so the description doesn't need to restate those. It adds the requirement about including conversation for reproduction, which is useful context. However, it does not describe what happens after reporting (e.g., confirmation, tracking), so transparency is limited but 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?

Two concise sentences, front-loaded with the purpose. Every word earns its place; no redundancy or filler. Ideal length for a tool description.

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 has 3 parameters, no output schema, and minimal annotations, the description is on the lean side. It states the core action and the key parameter, but lacks explanations for all parameters and any description of return values. It is minimally adequate but leaves room for improvement.

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 ('recent messages for reproduction'), but it does not explain 'message' (required) or 'context' at all. This leaves significant gaps for the agent to infer parameter meanings.

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.' The verb 'Report' is specific, and the resource (bug/feature/feedback) is clear. It distinguishes itself from sibling tools by its unique function, though siblings are unrelated, so no confusion arises.

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 what to include: 'Include the conversation array with recent messages for reproduction.' This clarifies a key usage context. However, it does not mention when not to use the tool or alternative tools, but since siblings are unrelated, 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. The description adds context by specifying what is returned (platform and adapter versions), which complements the annotations without contradiction. It does not add extra details about behavior beyond that, but for a simple query tool, this is sufficient.

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 captures the tool's purpose with no filler. It is appropriately short 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?

The tool is trivial with no parameters and no output schema. The description is complete for what it does. The annotations cover safety, and the description clearly states the purpose. No missing context.

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 schema has no properties. The description correctly implies no input is needed, so parameter semantics are trivially clear. Baseline 4 for no 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 uses a specific verb ('Show') and clearly identifies the resource ('MCP platform and adapter versions'). It is distinct from sibling tools like toolkit_info or marketplace, making its 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 implies usage (when you need version info) but provides no explicit guidance on when to prefer this tool over alternatives or any exclusions. Given its trivial nature, implied usage is acceptable but not fully explicit.

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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds context beyond annotations by listing exactly what information is returned (installed MCPs, connection status, accounts, catalog tool counts). This is useful for setting expectations, though it does not disclose any potential side effects (which are none) or access requirements. With good annotations, the description's addition is sufficient.

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 is concise and informative聲. It front-loads the primary purpose ('Returns the current toolkit state') and then lists the key details, with no redundancy or extraneous information. It earns its place perfectly.

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 simplicity of the tool (zero parameters, no output schema), the description fully covers what an agent needs to know. It explains the scope of the return information, which is sufficient for an agent to decide to call it. There are no gaps: no parameters to explain, no output schema to document, and annotations cover safety. The description is 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?

This tool has zero parameters, so there is nothing to document. The description adds value by clarifying the purpose and return content, which compensates for the lack of parameters. A baseline of 4 is appropriate for tools without parameters, given the description is clear and comprehensive.

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 this tool returns the current toolkit state, listing specific components: installed MCPs, connection status, connected accounts, and catalog tool count. This distinguishes it from sibling tools like 'connect' or 'authenticate', which are action-oriented, while this is informational.

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 for retrieving state information, but it does not explicitly state when to use it versus alternatives. Given zero parametersامd, it's clear it's a quick status check, but there is no explicit guidance on when to choose it over sibling tools like 'show_version' or 'marketplace'. A direct mention of when to use it (e.g., 'Use this to check overall status before making connections') would improve the score.

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