SENATRAN: Consultar Exame Toxicológico

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

Annotations already declare idempotentHint=true, destructiveHint=false, and readOnlyHint=false, which the description complements. The description discloses that calling with no args returns a login link (likely non-side-effectful), and with token establishes a session. It also explains a permanent vs. session behavior and mentions non-expiring connection vs. session-only, adding behavioral context beyond annotations. It does not explicitly mention that this is a safe operation, but annotations cover that. Minor gap: not stating what happens on invalid token, but overall strong.

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 but packed with information, and is front-loaded with the most important context (IDE agents). It uses a colon and dash to structure the two options (no args vs. token). Slightly long due to the parenthetical and example but every sentence earns its place. No fluff, but could be tightened slightly for easier parsing.

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 complexity (two distinct usage modes), the description is complete: it covers how to invoke both modes, the meaning of the token parameter, the permanent vs. session distinction, and even integration with server config. With no output schema, it doesn't need to explain return values, but it does say that no-args call 'get the link', which implies the output. The description covers all necessary context for an agent to use the tool 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% and the schema only has a 'token' property with no description. The description compensates fully by explaining the token parameter: it should be a JWT pasted by the user for session-only login, and omitting it yields the login link. It also differentiates between using the token parameter and setting a header. This adds significant meaning beyond the bare schema, earning a high score.

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 authenticates the user for IDE agents, with a specific verb ('log in', 'authenticate') and resource (the server connection). It distinguishes itself from siblings like 'connect' by focusing on token-based authentication vs. establishing a connection, and provides clear alternatives (config header vs. session-only token). The description is specific and action-oriented, making its 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 description provides explicit when-to-use guidance: it tells the agent to call with no args to get the login link, or with the token after the user pastes it. It also explains when not to use it (e.g., for permanent access, recommend config header instead of session token). It even mentions context (IDE agents like Cursor) and gives clear alternatives (config header vs. paste token). This is exemplary 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds valuable detail about output structure (authenticated, pending, connect_url) and how results vary based on connection state. This goes beyond what annotations convey, though it doesn't cover partial connection states or error handling.

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 primary purpose, and efficiently covers two distinct scenarios without fluff. Every sentence 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?

With no input parameters and no output schema, the description sufficiently explains the two main output states. However, it leaves ambiguity about intermediate states (e.g., some providers connected) and does not mention error or edge cases. Given the simplicity of the tool, this is adequate but not exhaustive.

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 does not need to explain parameter meaning. Baseline of 4 applies, and the description appropriately focuses on return behavior instead of 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, and explains behavior under two conditions (all connected vs. missing credentials). It distinguishes from sibling tools like authenticate (which likely handles authentication) and show_version (version info), though it doesn't name them explicitly.

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 checking connection status, but it does not explicitly state when to use it versus alternatives (e.g., 'use this to check if authentication is needed before calling authenticate'). It provides context about credential states but lacks direct comparison to sibling tools.

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?

Despite annotations already indicating write operations (readOnlyHint: false), the description adds rich behavioral context: invoke runs MCPs one-off without installing, returns connect/checkout links when auth/payment is needed, requires workspace owner/admin for writes, and flags installed status in search/describe. No contradiction with annotations; all statements align with the declared non-read-only nature.

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 dense paragraph, but the tool's 23-parameter action surface justifies length. It is front-loaded with the core flow and structured logically: purpose → core flow → invoke nuance → install guidance → other actions → permission caveat → prompt library. Some formatting (bullets) would improve scannability, but every sentence adds meaningful content.

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 multi-action gateway with no output schema, the description covers the essential workflows: search/describe/invoke/install, auth/payment handling, permission requirements, and the prompt library. Minor actions like 'resume' are not described, and return-value shapes are absent, but the major decision paths an agent needs are present. It is nearly complete for the tool's complexity.

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 but only partially compensates. It explains the 'action' enum values in the core flow and hints at tool_id/arguments via 'describe returns one MCP's full profile... so you pick the right tool_id' and 'invoke RUNS that tool.' However, many parameters such as limit, immediate, tier_slug, resume, and prompt_* are not individually clarified, leaving gaps for an agent.

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 clear definition: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then outlines the core flow (search → describe → invoke) and distinguishes itself from sibling tools by being the umbrella catalog that covers both discovery and execution. The verb+resource clarity is high, and it clearly differentiates from siblings like authenticate or report_bug.

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 decision criteria: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use,' and explains when to use list_tools, report_bug, and request_mcp. It also clarifies that invoke is functional even when the MCP is not installed, which is a key alternative to existing toolkits. This goes well beyond implied usage.

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 specify readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the core behavioral safety profile is known. The description adds value by requesting the conversation array for reproduction, but does not say what actually happens after the report is submitted, whether there is an acknowledgement, or if any external system is notified.

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 word is purposeful: the first sentence front-loads the tool's purpose then the list of use cases, and the second sentence directly provides actionable input guidance. There is no filler or repeated schema information.

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 relatively simple reporting tool, the description gives enough to satisfy likely use cases: what to report and what to include for reproduction. However, since no output schema and no return-style documentation exist, the agent is left guessing about the response or final outcome of a report submission.

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 for all three parameters. It explicitly instructs the use of the `conversation` parameter for reproduction and implies that `message` is the report content, but it completely omits `context` and leaves parameter format/default expectations vague. This only partially covers the parameter burden.

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 'Report' and identifies exactly what is being reported: bugs, missing features, and feedback. It differentiates from the sibling tools by making the bug/feedback scope explicit, though it leaves 'send feedback' somewhat broad.

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 context for when to use the tool: whenever the user reports a bug, requests a missing feature, or wants to send feedback. It also provides practical guidance by asking for the conversation array to help with reproduction. It does not explicitly compare to alternatives, but no sibling tool serves this same 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. The description adds meaningful context beyond those: it is hosted by the platform, requires no platform credentials, charges prepaid credit per query, and states the data is not confidential and the client is LGPD data controller. This is useful behavioral and legal context, though it omits output/error 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 moderately dense paragraph that front-loads the core purpose and then provides payment, credential, and LGPD context. It is not unnecessarily long, though the legal/payment details could arguably be condensed without losing meaning.

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 a simple read-only query with three required parameters and no output schema. The description covers purpose, source, payment, and legal responsibility, which is reasonably complete for tool selection. However, it does not describe the return format, possible empty results, error behavior, or date parameter formats, which matters more because no output schema is provided.

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?

Input schema coverage is 0%, but the description does not explain any of the three required parameters (cpf, birthdate, data_vencimento_cnh), their formats, or their roles. The resource type implies that CPF, birthdate, and CNH expiration date are needed for the query, but the description itself provides no parameter-specific meaning beyond the raw schema names.

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 a specific action ('Consultar Exame Toxicológico') targeting a specific resource (SENATRAN official toxicological exam data). It further distinguishes the tool by clarifying the official source, prepaid pay-per-query model, and non-confidential nature, making its purpose unambiguous even relative to unrelated 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 provides clear contextual guidance: use this tool to query official Brazilian SENATRAN data, with no platform credentials required, prepaid credit per query, and LGPD-related responsibilities. It does not explicitly name alternatives or when-not-to-use conditions, but the context strongly implies the intended use case.

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 false. The description adds the 'current' qualifier, clarifying it returns live state. It adds minimal but non-redundant context about platform vs adapter separation, which is useful 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?

One sentence, no fluff, technical terms clear. Every word earns its place. Exactly what conciseness should be.

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 trivial version-check tool with no parameters, no output schema, and comprehensive annotations, the description fully covers what an agent needs to know. The low complexity means completeness is easily achieved.

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, so the schema is fully covered (vacuously). The description does not need to add parameter details. According to the rubric, 0 params yields a baseline of 4, which is appropriate here.

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: 'current MCP platform and adapter versions.' This distinguishes it from siblings like 'toolkit_info' which may have broader scope. It is precise and 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 context—when you need version information—but does not explicitly state when not to use it or name alternatives. For a simple version tool, this is adequate context, though it lacks explicit 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?

Annotations already declare readOnly, non-destructive, and idempotent hints, so the description adds value by specifying the exact content of the returned state (connection status, accounts, catalog tool counts). It does not disclose additional behaviors like rate limits, but the annotations cover the main 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 a single, well-structured sentence that front-loads the main purpose and lists the returned information without redundancy. Every element contributes to understanding the tool's output.

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 simplicity (no parameters, no output schema), the description covers the essential return values. It could benefit from specifying the output format or structure, but for a status tool, the current level is sufficient and complete enough for an agent to invoke 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 the description does not need to add parameter context. Baseline for 0 params is 4, and the description appropriately focuses on output, which is correct.

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 current toolkit state with specific details (installed MCPs, connection status, accounts, catalog tool counts). It distinguishes from siblings like authenticate or connect, which perform actions, by focusing on status inspection.

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 toolkit status but does not explicitly state when to use it versus alternatives, nor provide exclusions or prerequisites. It is minimally adequate but not directive.

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