Conselho Regional de Odontologia SC: Cadastro

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

The description adds context beyond the annotations, explaining that the token can be permanent (via header) or session-only (via argument), and that calling with no args yields a link. This clarifies the behavioral outcome and token lifecycle. 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?

The description is a single paragraph but information-dense, covering permanent vs session tokens and invocation patterns. It's somewhat run-on but each clause adds value; no wasted words.

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 an authentication tool with no output schema and minimal annotations, the description covers the essential flow: obtaining a link, handling tokens, and the two modes. It doesn't mention errors or post-auth behavior, but that's likely not critical for this 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?

With 0% schema description coverage and a single 'token' property, the description fully compensates by specifying that it expects a JWT and that the parameter is optional (can be omitted to get a link). This provides all needed semantic meaning 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 conveys that the tool authenticates the user by obtaining an access token, with specific instructions on how to supply it. It doesn't explicitly differentiate from the sibling tool 'connect', but the name and content make the purpose obvious.

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 how to use the tool: either by configuring the token as a header for permanent access or by pasting a session token, and that calling with no args provides the auth link. It doesn't explicitly compare against alternatives, but it gives clear usage context and best-practice 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 read-only, idempotent, and non-destructive behavior, so the bar is lower. The description adds value by specifying output structure (authenticated, pending, connect_url) and the two states, which goes 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 two concise sentences with a clear structure: first states the main function, second elaborates on scenarios. No redundancy or unnecessary words.

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 primary return values and two key scenarios (all connected vs missing credentials). It does not mention partial connectivity or error cases, but given the simplicity of the tool and the presence of an output description, it is reasonably 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 no parameters, and the schema coverage is 100% (vacuously). Per the rubric, baseline is 3 when coverage is high. The description adds no parameter details because none exist, so no enhancement is needed.

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, using a specific verb ('returns') and a specific resource ('connection status and URLs'). It distinguishes itself from sibling tools like 'authenticate' by focusing on status, not 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 conditional scenarios (when all providers are connected vs credentials missing) but does not explicitly contrast with alternatives (e.g., when to use this over 'authenticate'). It gives implicit usage context but lacks explicit when/when-not 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?

Beyond annotations (readOnly, idempotent, non-destructive), the description adds meaningful operational details: requires prepaid credit, needs no platform credentials, data is public/non-confidential, and the client is data controller under LGPD. These are valuable context not present 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 moderately concise but includes extra legal/compliance details (LGPD) that may be less actionable for an AI agent. The key purpose is front-loaded, but some sentences could be trimmed for clarity.

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 one-parameter tool, the description covers purpose and operational constraints but omits explicit parameter explanation and any hint about output. Since there is no output schema, the agent may not know what to expect or how to format the input.

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% and the description does not explain the sole parameter 'inscricao'. It does not state that this is the registration number or any format/validation. The description fails to compensate for the schema gap, leaving the agent unclear on what to pass.

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 queries registration information from a specific official Brazilian body (CRO/SC), with a clear verb ('consulta') and resource ('Cadastro'). It is distinct from sibling tools like authenticate or connect, which are generic platform operations.

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 about payment (prepaid credit) and hosting but does not explicitly state when to use this tool versus alternatives or when not to use it. It implies use for checking official registrations but lacks direct comparison or 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?

Beyond the sparse annotations (readOnlyHint false, openWorldHint true), the description discloses key behavioral traits: invoke works without installation, returns connect/checkout links when needed, and distinguishes one-off vs permanent installation. It also explains that writes require owner/admin permissions, correcting any assumption that all actions are open. 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 a long block of text, over 500 words, covering multiple actions and flows. While informative, it is not concise and could be structured with bullet points or sections. It front-loads the core purpose but then dives into extensive detail, making it harder to scan quickly. It would benefit from tighter organization.

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 (23 parameters, 14 actions, plus a prompt library), the description is remarkably complete. It covers the entire lifecycle: search, describe, invoke (one-off vs install), install/uninstall, subscribe/cancel, report_bug, request_mcp, and prompt library operations. It also explains auth/payment handling and admin requirements. Without an output schema, it still gives enough context for an agent to use the tool 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?

Schema coverage is 0%, so description must add meaning. It explains core parameters like action (search, describe, invoke, install, etc.), mcp_id, tool_id, arguments (implied via 'runs that tool'), and prompt-related params (prompt_slug, prompt_vars, etc.) through the described flows. It does not enumerate all 23 parameters, but provides sufficient context for the main dispatch and policy decisions.

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 official mcp.ai marketplace, covering MCP catalog and execution. It specifies the resource (MCPs and prompts), actions (search, describe, invoke, install, etc.), and distinguishes from siblings by focusing on marketplace capabilities, unlike authenticate, show_version, etc.

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?

Provides explicit guidance: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT'. It explains when to use search/describe, when to use list_tools, when to use subscribe/cancel, request_mcp for missing needs, and prompt library actions. Also warns about auth and payment links, and specifies that writes require owner/admin.

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 provide readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description does not contradict these but adds minimal behavioral context. It mentions including the conversation array for reproduction, which hints at usage but doesn't describe side effects (e.g., that a report is sent). With annotations present, the bar is lower, but the description adds limited extra context about 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 two sentences, front-loaded with the primary purpose, and includes a necessary usage tip. Every word earns its place; no redundancy or fluff.

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 complexity (simple, 3 params, no output schema), the description covers the main purpose and mentions the conversation array. However, it leaves gaps: the 'context' parameter is unexplained, and the return or follow-up behavior is not described. For a bug-report tool, it may be adequate, but it could be more informative about expected outcomes and parameter details.

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. It explains the 'conversation' parameter by stating to include the conversation array with recent messages, which gives some meaning. However, it does not clarify the 'message' (though inferred as the bug report text) or 'context' (default empty, purpose unclear). Partial compensation, but not enough for full semantic clarity.

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: 'Report a bug, missing feature, or send feedback.' This is a specific verb (report) and resource (bug/feature/feedback), which clearly distinguishes it from siblings like authenticate or connect. No ambiguity.

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 (for reporting issues or feedback) and includes a practical instruction to include the conversation array for reproduction. However, it lacks explicit guidance on when not to use it or alternatives, though sibling tools are clearly different in scope. The context is clear enough for selection.

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, which cover the safety profile. The description adds the specific scope of what versions are shown (platform and adapter), but does not disclose additional behaviors such as error conditions or connection requirements. It does not contradict annotations, so the score is adequate but not exceptional.

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, concise sentence that is front-loaded and free of fluff. Every word earns its place, clearly conveying the tool's purpose without 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?

Given the tool's low complexity—no parameters, no output schema, and benign annotations—the description is sufficiently complete. It specifies exactly what is returned (platform and adapter versions), which covers the essential context for an agent to use the tool 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, and the input schema is completely described (coverage 100% vacuously). With no parameters, the description does not need to add parameter semantics. The baseline for 0 params is 4, and this holds since there is no 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 states the tool's function: 'Show the current MCP platform and adapter versions.' It uses an explicit verb ('Show') and specifies the resource (versions). This distinguishes it from sibling tools like authenticate or marketplace, which have different purposes.

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 is self-explanatory but does not provide explicit guidance on when to use this tool versus alternatives. While it's obvious for a version check, there is no mention of scenarios or comparisons with similar tools like toolkit_info. It only implies usage rather than stating it.

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, idempotent, and non-destructive. The description adds what the tool returns (installed MCPs, connection status, accounts, catalog counts) which goes beyond the annotations, but does not discuss side effects, error conditions, or dependencies (e.g., requires prior authentication). This is adequate given the annotations cover safety.

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, front-loaded with the verb 'Returns', and no filler words. Every word adds value by enumerating the response contents.

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 status tool, the description sufficiently enumerates the returned data (installed MCPs, connection status, accounts, catalog counts). It does not mention output format or potential errors, but for this simple tool, that is acceptable. The lack of output schema means the description must cover return content, which it does.

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 Apa yang, so schema coverage is 100% (vacuously). Baseline for 0 params is 4. The description does not need to explain 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 uses a specific verb ('Returns') and clearly identifies the resource ('current toolkit state') while enumerating its contents (installed MCPs, connections, accounts, counts). It is distinct from siblings like authenticate or connect, which are action-oriented.

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 clearly explains what the tool does, making it obvious when to use it (when you need to inspect toolkit state). It does not explicitly state when *not* to use it or name alternatives, but its purpose is so specific that it implicitly differentiates from siblings.

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