Conselho Federal de Biomedicina: Cadastro

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

The description explains behaviors beyond the annotations: it distinguishes permanent vs session-only auth, mentions the browser-based login flow, and specifies that no args returns a link. Annotations indicate idempotentHint=true and destructiveHint=false, and the description is consistent with these, adding useful context about token persistence.

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 somewhat long but every sentence serves a purpose: explaining the login flow, recommended permanent setup, and session-only alternative. It is front-loaded with the tool's core purpose before diving into mechanics.

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 one optional parameter and no output schema, the description covers the important use cases and invocation patterns. It could mention success/error behavior or what the login link response contains, but the core interaction is sufficiently explained.

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?

Though schema description coverage is 0%, the description compensates by explaining that 'token' is a JWT pasted by the user for session-only login, and that omitting it yields the login link. This adds meaningful semantic meaning beyond the bare 'string' type in the schema.

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 an authentication flow: logging in via browser and using the access token. It states the exact action ('log in', 'copy the access token') and distinguishes itself from sibling tools by specifying its authentication-link and token-acceptance behavior.

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 guidance: best practice is adding the token as a permanent config header; session-only login is achieved by passing { token: ... }; no arguments produces the login link. It clearly defines when to use each mode and how to invoke the tool.

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?

Beyond annotations (readOnly, idempotent, non-destructive), the description discloses that it requires prepaid credit, no platform credentials, and that data is non-confidential, plus LGPD compliance. This adds practical behavioral context not in 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 dense paragraph that mixes purpose, hosting details, payment, and legal obligations. It is not overly long but is not front-loaded with the most critical info (purpose) and includes extra legalese that could be trimmed.

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 query tool, it covers key facts (source, payments, credentials, data sensitivity) but omits details about return format, response contents, or how the credit system works. The lack of output schema makes this more noticeable.

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 two parameters (nome, registro) with zero description coverage. The tool description does not explain these parameters or their usage, leaving the agent without additional meaning. It fails to compensate for the schema's lack of documentation.

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 it is for 'consulta em fonte oficial' and specifically mentions consulting official Brazilian sources, clearly indicating a read/query operation. It is distinct from siblings like authenticate and marketplace, though the verb 'consultar' is not explicitly written but implied. 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?

The description provides context (hosted by platform, pay-per-query) but does not explicitly say when to use this tool vs alternatives or when not to use it. It implies use for checking official data but offers no comparison to other 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?

Annotations already establish this as a read-only, idempotent, non-destructive operation. The description adds meaningful behavioral context beyond that: it specifies the authenticated:true / empty pending[] return condition and the connect_url fallback when credentials are missing, giving agents a clear expectation of response shape.

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 core purpose, and every clause adds value by describing conditional behavior. There is no filler 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?

For a parameterless, read-only status tool with no output schema, the description covers the main return values under both relevant states (all connected vs missing credentials). It is sufficiently complete for an agent to know what to expect without additional documentation.

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 0 parameters, so there are no parameter semantics to explain; per the baseline for 0-param tools, a 4 is appropriate. The description compensates by explaining what the tool returns rather than input requirements.

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. However, it does not explicitly differentiate this tool from sibling tools like authenticate, so it falls just short of a 5.

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 use for checking connection state and retrieving connect URLs when credentials are missing, but it never offers explicit guidance on when to use this versus alternatives such as authenticate. It gives conditional behavior rather than usage recommendations.

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 annotations by disclosing that invoke runs one-off even when the MCP is not installed, that connect and checkout/top-up links are returned for auth/payment needs, that install makes an MCP permanent, and that writes require workspace owner/admin. It also reveals installed flag behavior and that prompt links open without login—rich behavioral context beyond readOnlyHint/destructiveHint.

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 information-dense; every sentence adds operational detail, and key concepts are front-loaded. It would benefit from bullet points or clearer separation of MCP flow vs prompt library, but the length is justified given the 14-action surface.

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 high complexity, no output schema, and no documented parameter details in the schema, the description provides a strong overview—covering workflow, permissions, auth/payment edge cases, and the prompt library—but stops short of enumerating per-action inputs and outputs (e.g., exact search/describe/list_tools response shapes). It is adequate for initial routing but incomplete for full invocation.

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 must compensate but only covers a subset: action, mcp_id, tool_id, arguments (implied), prompt_slug, and prompt_vars indirectly. Many parameters (limit, query, message, immediate, tier_slug, cancel_reason, request_details, report_context, conversation, etc.) receive no explanation, leaving agents without clear semantics for the full action set.

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 the mcp.ai marketplace—both a catalog of MCP/tools and the execution mechanism—and enumerates its core actions (search, describe, invoke, install, subscribe, etc.). It distinguishes itself from siblings like report_bug and authenticate by covering the marketplace-specific flow and prompt library.

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 usage guidance is provided: the core flow (search → describe → invoke) is laid out, invoke vs install is contrasted with a clear preference ('prefer invoke for a single/occasional use'), and list_tools is positioned as the way to see currently callable tools. The prompt library section also separates when to use search_prompts/get_prompt/publish_prompt, plus notes on permission requirements.

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 convey non-destructive and idempotent behavior. The description adds contextual guidance about what should be included for reproduction, but it does not disclose any deeper behavioral outcomes (e.g., ticket creation, server-side effects, response behavior). It provides some value beyond annotations but not rich detail.

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, immediately front-loaded with the tool's purpose and followed by a single actionable instruction. No filler or redundant 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 simple, low-parameter tool with no output schema, the description covers the core intent, use cases, and a key reproduction instruction. It is reasonably complete, though the `context` parameter remains underspecified and no return behavior is mentioned.

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 description coverage, the description bears the burden of explaining parameters. It clarifies the `conversation` parameter by describing it as an array of recent messages, and `message` is implied as the report content. However, the `context` parameter is left unexplained, and the description calls `conversation` an 'array' while the schema declares it as a string type, which could introduce ambiguity.

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's purpose with a specific verb and resource: 'Report a bug, missing feature, or send feedback.' This is unambiguous and distinct from the sibling tools, which are unrelated to bug reporting.

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 states the applicable contexts ('bug, missing feature, or feedback') and tells the agent to 'Include the conversation array with recent messages for reproduction.' It lacks an explicit when-not-to-use or alternative-tool reference, but no sibling is an obvious substitute.

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 value by specifying the tool reveals both MCP platform and adapter versions, which goes beyond the bare annotation metadata. No contradiction exists.

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, clear sentence with no filler. It is appropriately sized for a zero-parameter, read-only version display 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?

For a simple no-parameter version check with strong annotations, the description fully covers purpose and output scope. No output schema is necessary, and the tool is simple enough that nothing is left unexplained.

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 baseline is 4 per the rubric. The description does not need to explain any input semantics, and no information is missing.

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 the specific verb 'Show' and names the precise resource ('current MCP platform and adapter versions'). This clearly distinguishes it from sibling tools like 'authenticate' or 'connect', which serve entirely 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 provides no guidance on when to use this tool versus alternatives. With sibling 'toolkit_info' potentially overlapping as an informational tool, there is no exclusions or context to help an agent choose correctly.

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, giving the agent a safe profile. The description adds valuable context beyond annotations by specifying exactly what the returned state includes (MCPs, status, accounts, tool counts), which helps the agent anticipate the output without underselling it.

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 front-loaded with the core action ('Returns the current toolkit state') and then itemizes the content in a compact list. Every word earns its place; there is zero fluff 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 read-only state query with no parameters and no output schema, the description is complete. It enumerates all the components of the returned state, leaving nothing ambiguous about what the tool will report. No further details (pagination, formatting, etc.) are needed given the tool's simplicity.

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 schema coverage is trivially 100%. The description doesn't need to explain parameters; it focuses on the output. Baseline for 0 params is 4, and the description adds no unnecessary param-related noise, so it remains 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 returns the current toolkit state, specifying the exact contents: installed MCPs, connection status, connected accounts, and catalog tool counts. This verb+resource combination is explicit and distinguishes it from siblings like show_version (which likely returns version info) and authenticate/connect (which perform actions).

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 this tool: when you need to inspect the toolkit's current state (what's installed, status, accounts). It doesn't mention explicit exclusions or alternative tools, but the context is clear enough for an agent to recognize this as a status query. With no sibling that does exactly the same, the use case is unambiguous.

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