Conselho Regional de Odontologia MG: Cadastro

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

The description discloses that the tool can modify the server config (by adding a header) and can create a session token, implying side effects. However, it does not explicitly mention that it is non-destructive or describe potential consequences (e.g., overwriting existing config). Given the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true), the description aligns and provides enough transparency about the config change, but could be more explicit about side effects.

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 informative but a bit lengthy. It is structured with two clear options (permanent config and session-only) and an explanation of the no-arg call, which is efficient. However, the phrasing could be tightened slightly (e.g., 'add it to this server's config as a header' is slightly redundant with the later mention). Still, it remains focused and not overly verbose.

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 provides all necessary context for a first-time user: what the authentication is for, the two methods of using it, and how to invoke it. It does not specify return values, but since no output schema is provided, that is acceptable. The tool is fully covered in terms of steps and alternatives.

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 thoroughly explains the 'token' parameter: it should contain a JWT pasted by the user, and provides context for when it is optional (no args to get link). The schema only lists 'token' as a string with no description, so the tool description fully compensates and adds clear 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 clearly states the tool's purpose: authenticating to MCP.AI for IDE agents. It also distinguishes it from siblings (connect, cro_mg_cadastro_consultar, etc.) by focusing on authentication and providing specific usage instructions. The two options (permanent config vs session token) make the 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 guidance on when and how to use the tool: either adding the token to the server config for a permanent connection, or pasting it for session-only login. It also explains the no-argument call to obtain the link. This covers usage scenarios clearly, though it does not explicitly state 'do not use if...' but that is not necessary given the clarity.

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 transparently describes the tool's behavior under different conditions (all connected vs. missing credentials), specifying the exact output fields (authenticated, pending, connect_url). No contradictions 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 concise and well-structured, consisting of two clear sentences that cover the essential behavior without unnecessary 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?

The description fully explains the tool's output in both success and failure scenarios, providing sufficient context for an agent to interpret the results. No output schema is present, so the description compensates adequately.

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 no parameters, so the description does not need to add parameter details. The empty schema is adequately covered.

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: returning connection status and URLs. It distinguishes itself from siblings like 'authenticate' by focusing on status checking rather than performing 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 implies usage contexts (e.g., checking connection status, detecting missing credentials) but does not explicitly compare with alternatives like 'authenticate'. It provides enough context for an agent to decide when to use this 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?

Annotations already declare readOnlyHint=true and idempotentHint=true; the description adds useful behavioral context: no platform credentials required, prepaid per-query cost, data is the same as citizen-available (non-confidential), and client is LGPD controller. These details go beyond the annotations without contradicting them.

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; it conveys multiple pieces of info (source, cost, legal) but could be better structured. It is not overly long, but each sentence could be clearer; still, it is not bloated.

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?

There is no output schema, so the description should clarify what data is returned, but it only says 'consulta informação de fontes e órgãos oficiais'. It omits return fields, example usage, or any functional details about the consultation, leaving a significant gap for a simple one-parameter 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 description coverage is 0%, so the description must compensate, but it does not explain the single parameter 'inscricao' (e.g., format, expected values, or example). The parameter name hints at a registration number, but the description adds nothing beyond what the schema already shows.

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 indicates this is a query tool for CRO-MG registration data ('Cadastro, consulta em fonte oficial') but lacks a specific verb- resource structure and does not clearly state what is returned. It is distinguishable from generic platform siblings due to the explicit mention of the council and official source, so it is not a tautology but remains vague.

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?

No explicit when-to-use or alternative references are provided. Mentions prepaid credit and LGPD responsibility, but these are contextual disclaimers rather than actionable guidance on when to choose this tool over others or what scenarios it is appropriate for.

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?

Goes well beyond annotations, which only declare readOnlyHint=false and openWorldHint=true. The description discloses auth requirements ('Writes require workspace owner/admin'), side effects (invoke does a one-off install without bloating the toolkit), the non-install behavior of invoke, installed_in_toolkit vs installed_in_workspace flags, and cost/credential edge cases. 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?

Information-dense and every sentence largely earns its place given the enormous surface (14 actions + prompt library), but it is one unbroken 250+ word wall of text with no sectioning, headers, or prioritization. It could be split into MCP flow vs prompt library vs admin/billing sub-sections to aid rapid scanning. Appropriate in volume, weak in structure.

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?

Remarkably complete for the scope: covers the full discovery→run flow, install-vs-invoke decision, auth/owner requirements, billing/credential failure modes, and the entire prompt-library sub-flow (search/get/publish with return behavior: full text with {{variables}}, shareable mcp.ai/p/<slug> link). Given no output schema, it even explains key return behaviors (connect link, checkout link). Minor gaps remain for lesser actions (resume, list_tools output shape, subscribe specifics).

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 and 23 parameters, the description carries heavy burden and does compensate for the most critical ones: the full action enum (all 14 values explained with purpose), mcp_id/tool_id via the search→describe→invoke flow, and prompt_* params in the prompt library section. However, many parameters (limit, query, immediate, conversation, tier_slug, request_details, cancel_reason, report_context, prompt_targets) are never explicitly defined, leaving the 0% coverage only partially remedied.

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?

Exceptionally clear purpose: 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It names the specific resource (marketplace catalog), the core action flow (search → describe → invoke), and explicitly differentiates from siblings by noting report_bug/request_mcp and the separate prompt library. No ambiguity about what this meta-tool does.

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 when/when-not guidance: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use.' It distinguishes search/describe (discovery) from list_tools (what's callable now), names alternatives (request_mcp when nothing fits), and gives conditional workflows (connect link if credential needed, checkout link if wallet empty, 'then you retry').

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 does not disclose side effects beyond 'reporting', but the annotations cover readOnly and destructive aspects. It does not add extra transparency about persistence or idempotency, though not contradictory.

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 brief and to the point—one sentence that conveys the main purpose without unnecessary elaboration.

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 lacks clarity on all parameters and does not mention any output or expected behavior. It is not complete enough for a user to understand the full scope, especially since the schema provides no additional guidance.

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?

Only 'conversation' is mentioned, but not its format (JSON string) or purpose clearly. 'context' and 'message' are not explained at all, leaving their semantics vague.

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 as reporting bugs, missing features, or feedback. It differentiates from sibling tools by focusing on issue 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 implies usage when a user encounters a problem, but does not explicitly mention when to use it over alternatives or provide any usage conditions.

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 idempotentHint=true, indicating a safe, non-mutating operation. The description adds minimal behavioral context, just stating what version info is shown. It neither contradicts annotations nor adds details about output format or potential network calls, but for a simple version check, the annotations cover the main behavioral concerns.

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 with no fluff. It clearly states the tool's output without unnecessary details. Ideal conciseness for a simple 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 simplicity (no params, no output schema, annotations cover safety), the description is fairly complete. However, it doesn't specify the exact output format or where the information comes from (e.g., local vs remote), which could matter for agents. But given the low complexity, it's adequate.

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 schema description coverage is 100% (vacuously). The description adds no parameter info because none exist. The baseline for zero parameters is 4, and the description's mention of 'platform and adapter versions' provides a hint of the output content, which is sufficient.

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: showing current MCP platform and adapter versions. It distinguishes from siblings by being a version info tool, though it doesn't explicitly compare to sibling names like 'toolkit_info' which might overlap.

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 explicitly state when to use this tool versus alternatives. It implies usage for checking versions, but no explicit context or exclusions are provided. Sibling tools like 'toolkit_info' might offer similar information, but no guidance is offered.

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 (readOnlyHint, idempotentHint) already disclose side-effect profile. The description supplements by clarifying the returned state details, fully aligning with the annotations and adding useful context 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?

The description is a single, clear sentence with no superfluous content. It efficiently conveys the tool's function and output scope.

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?

Since there is no output schema, the description fully specifies what the tool returns (installed MCPs, connection status, accounts, catalog tool counts), making it contextually complete for users.

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 adds no parameter semantics beyond the schema. Per rubric, zero params baseline is 4, and there is nothing to improve.

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 with a specific verb ('Returns') and resource ('toolkit state'), listing the exact information provided (installed MCPs, connection status, accounts, catalog counts). It is distinct from sibling tools like 'authenticate' or 'connect'.

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 explains what the tool does but does not explicitly state when to use it relative to alternatives. It is implied as the go-to for state inspection, but no direct 'use this when...' guidance is provided.

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