MPT SE: Certidão Negativa de Feitos

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

Annotations include idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description adds that the token can be non-expiring when added to config, and explains the session vs permanent distinction. It does not contradict annotations, and adds useful behavioral context beyond annotations, though it does not discuss potential side effects (like creating a session) explicitly, but the idempotency hint covers that.

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 bit long (two sentences with parentheticals) but every clause adds necessary info: audience, method, permanent vs session, and argument usage. It is structured logically, though it could be tightened without losing value. It is front-loaded with the main action.

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 1 optional param, no output schema, and annotations, the description covers the essential context: how to authenticate, the two modes (config vs session), and what the agent should do (call with token or no args). It doesn't specify the return value (e.g., link), but that is implicit. It is complete enough for a simple auth tool, though a note on error cases could be added.

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%, but the description explains the only parameter 'token' as a JWT to be pasted. It gives clear usage context: with token for session login, without token to get link. This adds semantic meaning beyond the bare schema, which only says 'type: string'. Since there is only 1 param and it's fully described, this is strong.

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 states the purpose: authenticate by logging in via browser and copying an access token, with options for permanent config or session-only paste. It clearly identifies the resource (authentication) and the action (authenticate), though it could be more concise. It does not explicitly differentiate from sibling tools, but the purpose is clear enough.

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 when-to-use guidance: for IDE agents like Cursor, log in via browser, copy token, and either add to config for permanent connection or paste for session-only login. It also explains the argument variations (with token, with no args) and the context (after user pastes). This is comprehensive and actionable.

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 read-only, idempotent, non-destructive behavior. The description adds value by explaining the exact response conditions (e.g., when 'authenticated:true' and empty 'pending[]') and the inclusion of 'connect_url' and per-install URLs. It does not over-explain, and 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?

Two concise sentences front-load the main purpose and then provide clarifying conditions. Every word earns its place, with no fluff or redundant explanation.

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 endpoint with no output schema, the description covers the essential return fields and edge cases (all providers connected vs. missing credentials). It does not cover potential error handling or rate limits, but these are less critical for this simple 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?

There are zero parameters, and schema coverage is 100%. According to the rubric, a baseline of 4 is appropriate for 0-param tools. The description could not add parameter details, but the baseline is justified.

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 resource ('connection status and URLs') and clearly outlines expected output fields ('authenticated:true', 'pending[]'). This differentiates it from sibling tools like 'authenticate' or 'marketplace' by implying it's the status-check endpoint without explicitly naming alternatives.

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 when to use it (checking connection status, when credentials are missing) but does not explicitly compare to alternatives or state when not to use it. It provides context but no explicit exclusions or direct references to sibling tools, resulting in implied usage rather than clear 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 goes well beyond the sparse annotations by disclosing that writes require workspace owner/admin, that invoke runs tools one-off without installing them, and that paid/credential-gated MCPs return checkout/connect links. No contradiction with readOnlyHint=false or destructiveHint=false.

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 but front-loaded with purpose and core flow, and nearly every sentence adds a distinct behavioral fact. It is long, but the 14-action/23-parameter surface area justifies the length; a bit more structure would help.

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?

It thoroughly covers the marketplace search/describe/invoke lifecycle, install-vs-invoke tradeoffs, permission requirements, and prompt library. But it omits several actions/params (resume, immediate, tier_slug, conversation, prompt_tool, cancel_reason, etc.) and there is no output schema to compensate, so it is not fully 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 coverage, the description carries the full burden, and it does explain the central action values and the tool_id flow. However, many parameters (limit, query, immediate, tier_slug, conversation, cancel_reason, prompt_tool, prompt_targets, arguments, etc.) are never mentioned or mapped to actions, so the agent is left to infer their meaning.

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' and then details the core search→describe→invoke flow, making the tool's role unmistakable. It does not explicitly contrast itself with sibling tools like toolkit_info or connect, so it stops short of full sibling differentiation.

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?

Explicit guidance abounds: 'prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT', and 'request_mcp asks us to build a NEW MCP when nothing fits.' It also explains the retry flow for connect/checkout links, which tells the agent exactly when and how to proceed.

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 valuable behavioral context: it is paid per query (prepaid credit), requires no platform credentials, and returns the same non-confidential data available to citizens, plus LGPD compliance responsibilities. No contradictions.

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 and front-loaded with the core purpose. It includes necessary operational details (payment, credentials, data classification) but is slightly wordy, particularly the LGPD clause. No fluff, 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 tool has no output schema, so the description should clarify expected results. It explains cost and data source but does not describe what the response contains (e.g., certificate validity) nor that a CPF or CNPJ is required. Given its simplicity, the missing return-value info and parameter guidance leave notable gaps.

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 has two string parameters (cpf, cnpj) with no descriptions, and schema description coverage is 0%. The description does not explain that these are Brazilian taxpayer ID types, that at least one is required, or how they relate to the certificate query. It merely repeats the general purpose, leaving the agent without guidance on parameter values.

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 'MPT SE: Certidão Negativa de Feitos, consulta em fonte oficial' which clearly states the verb (consulta) and the resource (Certidão Negativa de Feitos from MPT SE). It further explains that it queries official Brazilian sources, distinguishing it from sibling tools like authenticate and connect which are platform-level operations.

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: it is hosted by the platform, requires no platform credentials, and charges per consultation via prepaid credit. This implies when to use the tool (for paid official data queries). However, it does not explicitly state when not to use it or name alternative tools, so it falls short of a 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 mark that the tool is not read-only and is not destructive. The description adds some context by asking for the conversation array for reproduction, indicating that data is sent for diagnosis. However, it doesn't describe what happens after the report is sent, persistence, rate limits, or possible errors. This is a middle ground with annotations carrying part of the burden.

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 and front-loads the primary purpose. It wastes no words and includes practical guidance about the conversation array. However, it could compress the paraphrase of the tool name and instead provide more schema-guiding parameter detail.

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 feedback/report tool, the description is adequate. The annotations cover read/write/destructive traits, and the description notes the key reproduction input. Yet it omits the purpose of context, gives no indication of the response/return value, and doesn't clarify whether the report is immediately submitted or stored locally. This leaves some ambiguity for an AI 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?

Schema has zero descriptions for all 3 parameters, so the description must shoulder more weight. It explains the 'conversation' parameter's purpose (include recent messages) and implicitly ties 'message' to the bug/feedback content, but 'context' remains undefined. Parameter semantics are partially compensated but not complete.

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 a specific verb ('Report') and target resource ('a bug, missing feature, or send feedback'). This distinguishes it from sibling tools like authenticate, connect, marketplace, and show_version, which serve clearly 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 makes the intended use explicit: report a bug, missing feature, or send feedback. It doesn't explicitly mention when not to use it or name alternatives, but the sibling tools are unrelated, so the implied usage is sufficient. The reproduction hint also helps guide proper 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that the tool returns platform and adapter versions, but it does not disclose output format or any additional behavioral traits.

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 with no filler or redundancy. Every word contributes to understanding what the tool does.

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 query with strong annotations and no output schema, this description is sufficiently complete. It tells the user exactly what information is displayed and leaves no critical gaps for the intended use case.

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 an empty input schema, so there is nothing for the description to elaborate on. The baseline score of 4 applies, and the description is sufficiently clear without adding parameter details.

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 showing current MCP platform and adapter versions. It is unambiguous and specific, though it does not explicitly differentiate itself from the sibling 'toolkit_info' tool, which could also be expected to return version-related information.

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 usage context is implied: use this tool when you need the current platform or adapter version numbers. However, there is no explicit guidance on when to prefer this over alternatives such as toolkit_info, nor any mention of 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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is established. The description adds behavioral context beyond annotations by specifying what the returned state includes (installed MCPs, connection status, accounts, catalog tool counts), which is valuable since there's no output schema. 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 well-structured sentence that front-loads the action ('Returns') and major subject ('the current toolkit state') before listing the four included aspects. Every part earns its place with no redundancy or filler, making it highly scannable and appropriately sized.

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 low complexity (0 parameters, no output schema), the description fully covers what the agent needs to know: the general purpose and the specific data points returned. It doesn't need to explain return formatting or side effects because the description already enumerates all major content areas, making it complete for this informational 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 tool has zero parameters, and the schema is empty, so there is no parameter ambiguity. According to the calibration baseline, a 0-parameter tool receives a baseline of 4, which is appropriate here as there is nothing to compensate for in the 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 the tool's function with a specific verb ('Returns') and resource ('the current toolkit state'), then enumerates concrete contents: installed MCPs, connection status, connected accounts, and catalog tool counts. This distinctively separates it from sibling tools like show_version, authenticate, and connect, which serve 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 when to use the tool: whenever the agent needs to inspect the toolkit's current state, such as checking installed MCPs or connection status. It does not explicitly list exclusions or alternative tools, but the scope is self-evident for a read-only informational tool, providing clear context without naming alternatives.

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