ANVISA: Bulário Eletrônico

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 description's burden is lower. The description adds valuable behavioral context: it requires prepaid credit, does not require platform credentials, returns non-confidential official data, and includes LGPD compliance responsibilities. This goes beyond the annotations and helps the agent understand the operational and legal context without contradicting 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, with three sentences that convey essential operational and legal details. It opens with the core purpose ('consulta em fonte oficial') and then provides payment and data-privacy context. There is slight redundancy (e.g., 'fontes e órgãos oficiais' and 'a mesma disponível ao cidadão' repeat the idea of official/public data), but overall it is well-organized and front-loaded with the most important 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?

The tool has six parameters, zero required, and no output schema. The description does not explain what the tool returns (e.g., medication leaflet details, warnings, dosage), nor does it describe how the parameters interact (e.g., whether all are optional, how date ranges work). While the description covers payment and data governance, it leaves the query semantics and result format completely unexplained. For a lookup tool with this many parameters, the description is incomplete.

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 missing parameter documentation. However, the description does not mention the parameters at all. The parameter names are self-explanatory in Portuguese (e.g., nome_medicamento, data_inicial), but the description provides no additional details about required fields, formats, or relationships. This is a significant gap, as the agent has no guidance beyond the parameter names themselves.

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: it performs a consultation (consulta) in the ANVISA Bulário Eletrônico, an official Brazilian source. The verb 'consultar' and the resource 'Bulário Eletrônico' are explicit, and the description emphasizes it accesses the same data available to citizens. This distinguishes it from sibling tools (platform utilities like authenticate, marketplace) which have completely 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 usage for querying official Brazilian healthcare information, but does not explicitly state when to use this tool versus alternatives. It mentions the tool is hosted on the platform and requires prepaid credit, but does not discuss any other lookup tools or exclusions. The context of official data (not confidential, LGPD compliance) gives some guidance, but there is no direct comparison or when-not-to-use statement.

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 indicate idempotent, non-destructive. Description adds meaningful behavior: explains permanent vs session-only login, and that no arguments returns an auth link. This goes beyond the schema and annotations, though it doesn't describe the exact return structure or potential side effects on existing tokens.

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 sentences, front-loaded with the purpose and usage. The inclusion of the config recommendation adds length but is necessary context. No fluff, though it could be slightly 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?

Explains both usage modes and the token nature, but does not describe the output format (what the link looks like, what a successful login returns) or error conditions. Since there is no output schema, this is a gap.

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 only defines an optional 'token' string. The description clarifies it's a JWT for session-only login and that omitting it fetches a link. This adds meaning beyond the bare schema, earning above the baseline 3.

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?

Purpose is explicit: authenticate the user via login token. It distinguishes itself from siblings (like 'connect') by clearly stating it's for authentication and provides two methods (config vs session token). The verb+resource is specific.

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?

Description provides explicit when and how: 'Best: add it to this server's config' and 'call with { token: ... }' or 'with no args to get the link'. It gives clear alternatives and a recommended approach, effectively guiding an agent on 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 declare readOnlyHint=true and destructiveHint=false. The description adds valuable context about conditional return states (authenticated:true with empty pending[] vs. connect_url when credentials are missing), going beyond the safety 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 clause adds meaningful detail. No filler 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 zero-parameter read-only status tool, the description covers the key return scenarios: all connected vs. missing credentials. It sufficiently explains the output structure (authenticated, pending[], connect_url) without requiring an 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 tool has zero parameters and 100% schema coverage (empty schema), so there is no parameter information needed. Baseline for 0 params is 4; the description does not need to add anything.

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 verb+resource. It also distinguishes from siblings like 'authenticate' by explaining the output conditions, making the 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 context is clear: use this to check connection status and obtain URLs. It does not explicitly name alternatives or exclusions, but the behavior description implicitly distinguishes it from 'authenticate' (which would initiate connection) and other info 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?

The description adds meaningful behavior beyond annotations: invoke works even if MCP is not installed, returns connect/checkout links, requires owner/admin for writes, and flags install status. It does not contradict annotations and covers important side effects and prerequisites.

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 well-structured: it opens with the main purpose, explains the core flow, contrasts invoke vs install, lists other actions, then covers the prompt library. It is dense with useful information; however, some sections could be tightened.

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 parameters, the description provides a strong overview of main behaviors and flows, including auth, payment, and permanent installation. It does omit details for some secondary actions (e.g., resume, report_bug specifics) but remains largely complete for practical use.

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?

Given 0% schema description coverage, the description carries the burden. It explains the meaning of key parameters (action, mcp_id, tool_id, arguments, prompt_vars) and their roles in flows, but does not systematically cover all 23 parameters or specify formats for all.

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 it is the official mcp.ai marketplace and catalog, plus a way to run MCPs and access a prompt library. It distinguishes itself from sibling tools (e.g., authenticate, connect) by outlining its unique capabilities and core flow of search/describe/invoke.

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?

It provides explicit guidance: 'prefer invoke for a single/occasional use' and 'use install only to make an MCP PERMANENT'. It also explains when to use search/describe, list_tools, and other actions, and covers the prompt library separately.

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=false and destructiveHint=false, so the description adds the conversation for reproduction context. It doesn't disclose additional behavioral traits like auth requirements or side effects, but the bar is lower given annotations. No contradiction found.

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 sentences, zero waste. The purpose is front-loaded, and the instruction about conversation is useful. Perfectly concise.

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 is incomplete given that it has 3 parameters and no output schema. It fails to clarify the required 'message' parameter, lacks any information about the return value or post-submission behavior, and only partially addresses parameter semantics. For a simple tool, it still leaves ambiguity.

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 explain parameters. It explains the 'conversation' parameter (recent messages for reproduction) but does not explain 'message' (required) or 'context'. This is a significant gap since 'message' is required and its content is ambiguous.

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: reporting bugs, missing features, or feedback. It specifies the action ('Report') and the resource (bug/feature/feedback), and includes an instruction to provide conversation context for reproduction, which distinguishes it from unrelated sibling 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 gives clear context on when to use the tool (for bug reports, feature requests, feedback) and provides guidance on what to include (conversation array). However, it doesn't explicitly state when NOT to use it or mention alternatives, but given no similar sibling tools exist, this is sufficient.

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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which the description aligns with—no contradiction. The description additionally clarifies that output is limited to 'MCP platform and adapter versions,' adding specific output 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 a single, focused sentence that wastes no words. It front-loads the action ('Show') and immediately provides the object, making it immediately actionable for an agent.

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 tool with strong annotations, the description is fully complete—it specifies exactly what information is returned and implies no additional prerequisites. No output schema is needed, and the scope is clear.

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 is trivially 100% covered. The rubric sets a baseline of 4 for such cases, and since there are no parameters to document, this score is appropriate.

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 'Show the current MCP platform and adapter versions' using a specific verb ('Show') and resource, which is unambiguous and distinct from sibling tools like connect or authenticate. It fully addresses what the tool does without being tautological.

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—it's a version-checking tool—but does not explicitly state when to use it or compare against alternatives. There is no mention of exclusions or context like troubleshooting, making it 'implied usage' as defined by the rubric.

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 agent knows it is a safe read operation. The description adds the scope of the returned state but does not disclose additional behaviors (e.g., network dependency, auth requirements, error patterns), which is acceptable given the strong annotation coverage.

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 front-loads the primary purpose and enumerates the specific return fields without any filler or redundancy. Every word contributes to understanding the tool.

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 (no parameters), the presence of safety annotations, and the absence of an output schema, the description adequately enumerates all the information the agent will receive. It covers the full scope of the returned state, making the tool's functionality sufficiently 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?

The tool has zero parameters and an empty input schema, so there is no parameter ambiguity to resolve. The baseline score of 4 for no-parameter tools is appropriate; the description needs no additional parameter 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 uses a specific verb 'Returns' and clearly identifies the resource ('current toolkit state') with enumerated details (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from sibling tools like show_version or authenticate, which address 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?

The description implies that the tool should be used when an agent needs an overview of the toolkit's state, but it does not explicitly state when to use it over alternatives or mention exclusions. No direct comparison to sibling tools is provided.

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