ANVISA: Funcionamento de Empresa Nacional

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

The description explicitly notes the data is not confidential ('não é dado sigiloso'), confirms it's the same data available to citizens, and addresses LGPD compliance responsibilities. It also discloses the payment model (prepaid credits) and hosting context. While annotations declare the operation read-only, the description adds significant context about data sensitivity, legal compliance, and usage costs beyond what annotations capture.

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 block of text providing substantial information, but it is not front-loaded with the most critical information first and covers multiple unrelated topics (data source, payment model, LGPD compliance) in one paragraph. A more structured approach with shorter sentences or bullets would improve scanability.

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 covers purpose, data source, legal compliance, and access requirements, which is comprehensive for a simple tool with a single parameter. It doesn't need to explain return values since there is no output schema, and the information about data ownership and legitimate purpose expectations adds valuable context beyond the basic query function.

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 0% coverage for the 'cnpj' parameter, meaning the description must compensate. The description implies the tool queries based on company identification but doesn't explicitly explain the CNPJ format, validation rules, or how to handle formatting. The description is about the data source and compliance, not the parameter itself, missing the opportunity to provide necessary format or usage details for 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 identifies the tool as querying ANVISA for national company operation status ('Funcionamento de Empresa Nacional'), specifying the official source ('consulta em fonte oficial') and data type. While it clearly states the resource and verb, it doesn't emphasize sibling differentiators because siblings like 'authenticate' or 'report_bug' are distinctly different tools, making the purpose strong but not perfectly scoped to distinguish between similar query tools.

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 it's hosted on the platform, paid per query with prepaid credits, and that credentials are not required from the platform. However, it doesn't explicitly say when to use this tool over alternatives or when not to use it, leaving an implied usage context at best.

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 having annotations (idempotentHint: true, readOnlyHint: false), the description adds significant behavioral context: it explains that the tool initiates a browser login, produces a token, and that the token can be used either permanently or for a session. It also discloses that calling with no args returns a link for the user to authenticate, and that passing a token after the user pastes it establishes a session. This goes beyond 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 a single paragraph but is well-structured and front-loaded with the key context (MCP.AI for IDE agents). It is concise, with no redundant sentences; every sentence adds value, explaining the two authentication paths and the parameters.

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 (one optional parameter, no output schema, and annotations covering idempotency and non-destructiveness), the description is adequately complete. It covers the core workflow, the two usage scenarios, and the parameter semantics, leaving no major gaps for an agent to misinvoke.

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 only defines a 'token' parameter with no description, so the description must compensate. It does: it explains that the 'token' parameter is the JWT pasted by the user for session-only logincy, and that calling without it fetches a login link. This adds crucial meaning to the parameter, but it does not cover edge cases like token validation or error handling.

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: to authenticate the user by obtaining an access token via browser login and then either configuring it permanently or using it for a session. It specifies the action (log in, copy token, call with token) and distinguishes itself from siblings by focusing on authentication.

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 guidance on when and how to use the tool: it explains the two modes (permanent config vs. session-only), and instructs to call with no args to get the login link, or with the token after the user pastes it. It even mentions a best practice (adding to config as a header) and a conditional (session-only login), covering both 'how' and 'when'.

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 discloses the return behavior in detail (authenticated and pending fields, connect_url in case of missing credentials). This aligns with the read-only and idempotent annotations, and provides additional context 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?

The description is concise, using two sentences to convey the essential information without redundancy. The structure is clear and easy to parse.

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 covers the main return scenarios and fields (authenticated, pending, connect_url), which is sufficient for a simple tool with no parameters or output schema. Minor missing details about the exact response structure are not critical.

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 no parameters, so the schema is fully covered. The description correctly omits parameter explanations, as there is nothing to add.

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, which is a specific purpose. It does not explicitly contrast with sibling tools like 'authenticate', but the focus on status and URLs is distinct 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?

The description does not provide explicit when-to-use guidance or contrast with alternatives. It implies behavior in two scenarios (connected vs. missing credentials) but does not advise when to choose this tool over 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?

Discloses key behavioral traits beyond annotations: invoke runs tools even when not installed, write operations need owner/admin, invoke returns connect/checkout links on auth/payment failures, and install makes MCPs permanent. This adds significant context beyond the annotations (readOnlyHint false, openWorldHint true, etc.) without contradiction.

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?

Description is a single large paragraph but every sentence adds value, covering the core flow, key distinctions, and the prompt library. It uses arrows for sequential steps, aiding readability. Though not broken into sections, it is appropriately sized for the tool's complexity.

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 23 parameters, no output schema, and multiple action families, the description covers essential usage patterns and edge cases (auth, payment, installation). It explains the prompt library succinctly. While not every parameter is documented, the description provides enough for an agent to correctly select and invoke the 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?

Schema coverage is 0%, but description compensates by explaining the core action parameter and its values (search, describe, invoke) and referencing related parameters like mcp_id, tool_id, and arguments in context. It does not detail all 23 parameters individually, but the major ones are meaningfully described, justifying a score above baseline.

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?

Description clearly identifies the tool as the official mcp.ai marketplace, serving as both a catalog and execution platform. It distinguishes from sibling tools by outlining its comprehensive scope, including searching, describing, invoking, installing MCPs, and a prompt library, which no sibling covers.

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?

Explicitly explains when to use each action (search, describe, invoke, install, subscribe, cancel, etc.) and contrasts invoke vs install, noting when each is appropriate. Also describes the prompt vs MCP distinction and mentions that writes require owner/admin, giving clear usage context and alternatives.

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 mentions including the conversation array for reproduction, which adds insight into how the tool uses input. Annotations already cover idempotency and non-destructiveness. While it doesn't describe post-submission effects, the description provides reasonable transparency 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?

The description is a single sentence that directly states the tool's purpose and one key parameter usage. It is front-loaded with the primary action and avoids unnecessary detail, making it easy to parse.

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 reporting tool with no output schema, the description gives enough context about what the tool does and a hint about the input. It could mention that the message is required and what happens after submission, but overall it is complete for the tool's apparent scope.

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 description explains the purpose of the 'conversation' parameter but says nothing about 'message' (which is required) or 'context'. Since schema coverage is 0%, the description only partially compensates for the lack of field-level guidance, leaving key parameters undocumented.

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 reports bugs, missing features, or sends feedback, which is a specific and distinct purpose. It differentiates from sibling tools like 'authenticate' or 'show_version' that serve different functions.

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 (when a bug or feedback is needed) but does not explicitly rule out alternative tools. Given the sibling list includes no similar reporting tools, the usage scenario is clear enough, though a brief 'use this to submit' would be more 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds no extra behavioral nuance (e.g., output format or precision) beyond the obvious 'show versions', which is adequate for a trivial read-only tool.

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, front-loaded with the verb and object, with zero wasted words. It directly conveys 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, no-output-schema tool, the description is complete enough: it states what is shown. It could optionally hint at the return format (e.g., 'returns version strings'), but the phrase 'Show' implies a readable output. Given the simplicity, it meets adequacy.

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 the baseline is 4. The description does not need to add parameter details, and the schema already indicates zero 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 states a specific action ('Show') and a specific resource ('current MCP platform and adapter versions'), which clearly distinguishes it from sibling tools like toolkit_info or authenticate. It is not a tautology and provides 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 gives clear context (displays version info) but does not explicitly mention when to use it versus alternatives. It implies use when needing version information, and there are no exclusions or conflicting tool names that would confuse.

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, destructiveHint=false. The description adds context about the specific data returned (installed MCPs, connection status, accounts, counts). This goes beyond the annotations by specifying what the read-only operation actually reports, which is useful. No contradiction with annotations. A high score is justified because annotations cover safety and the description adds scope.

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, direct sentence that packs all necessary information without fluff. It is front-loaded with the key verb 'Returns' and lists the specific components of the returned state. Every element serves a purpose, and it is 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 that there are no parameters, no output schema, and annotations already cover safety/idempotency, the description provides a complete picture of what the tool does. It might optionally mention whether the output is dynamic or cached, but that is not critical. The description is sufficient for an agent to understand the tool's function and outcome.

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 0 params is 4, and the description indeed adds no parameter info because there are none. The description's mention of what is returned indirectly tells the agent what to expect without parameters. This meets the baseline.

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: returns current toolkit state including installed MCPs, connection status, connected accounts, and catalog tool counts. It uses a specific verb 'Returns' and a clear resource 'toolkit state', and it is distinct from sibling tools like 'show_version' which likely only reports 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?

The description implies usage: call it to get an overview of the toolkit's configuration and status. It doesn't explicitly contrast with sibling tools, but the clear scope (toolkit state vs. version, connection, etc.) provides adequate context for selection. No explicit exclusions or alternatives are mentioned, so it loses one point.

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