Conselho Regional de Odontologia TO: Cadastro

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

The description discloses that authentication can be permanent (via config) or session-based (via token), and implies that calling with no args initiates a browser login flow. It does not explicitly mention side effects like token replacement or logout, but the information provided is sufficient for typical use and aligns with the annotations (readOnlyHint=false, idempotentHint=true).

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 slightly verbose due to including both permanent and session options, but it remains focused and avoids unnecessary fluff. Each sentence adds value, explaining the token acquisition and usage methods. Minor redundancy (e.g., 'log in in the browser') but overall concise enough.

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 complete context: what the tool does, how to obtain the token, how to use it (permanent vs. session), and what happens when called with no args. No output schema is present, but the tool's behavior is sufficiently described for a user to understand its effect and expected outcomes.

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 parameter 'token' is clearly explained as an access token (JWT) obtained from the browser. The description shows exactly how to pass it: `{ token: "<jwt>" }`. This fully covers the parameter's purpose and expected format.

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 via an access token or via a browser login link. It is specific and distinguishes itself from sibling tools like 'connect', 'marketplace', etc., which 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 provides explicit instructions on how to use the tool: either by adding a permanent configuration header or by passing a token for a session-only login. It also mentions that calling with no args retrieves the login link. However, it does not explicitly state when to prefer this tool over alternatives, though the guidance is clear enough.

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, covering safety. The description adds behavioral context by explaining how the return structure varies with connection state (e.g., authenticated:true vs. connect_url). This goes beyond annotations and clarifies expected responses, though it could be more explicit about error scenarios or edge cases.

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, tightly written, and front-loaded with the core purpose. Every sentence contributes meaning: the first states the general return, the second explains the two states. There is no fluff 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?

Given the tool's simplicity (no parameters, no output schema), the description is largely complete. It covers both main scenarios (all connected vs. missing credentials) and indicates what is returned. It could mention whether other fields exist (e.g., individual provider statuses) but that is not necessary for a status check. Overall, it is adequate for an agent to understand the tool's functionality.

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 schema is empty with 100% coverage (nothing to cover). Per the rubric, a baseline of 4 is appropriate when there are no parameters, and the description does not need to compensate for any schema gaps. The description focuses on output behavior, which is correct for a parameterless tool.

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 returns connection status and URLs, with specific behavior for authenticated vs. unauthenticated cases. The verb 'returns' plus the resource (connection status) is specific, and it distinguishes itself from sibling tools like 'authenticate' and 'toolkit_info' by focusing on status rather than action or general 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 provides useful context on when to expect certain results (all providers connected vs. missing credentials), which implies usage for checking connection state. However, it does not explicitly state when not to use it or name alternative tools for different scenarios (e.g., 'authenticate' for initiating auth), so it falls short of a 5.

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, so the description doesn't need to restate that. It adds context about payment per query, prepaid credits, and LGPD data control responsibilities, which is useful. It doesn't contradict annotations; it complements them with operational details.

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 dense with relevant operational info: official source, payment model, data nature, LGPD disclaimer. It's well-structured and front-loaded with the main purpose. Every sentence adds value; no 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?

The tool is simple with one parameter and no output schema. The description covers purpose, data source, and legal context. It doesn't mention return format, but that's not required given the simplicity. The LGPD note adds compliance context that is important for usage.

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 doesn't explain the parameter 'inscricao' beyond what the schema shows (a string). Schema coverage is 0%, so the description could have elaborated, but it doesn't. However, the purpose is clear and the parameter name is self-explanatory (registration number). This is a minor gap.

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 consults dental council records (CRO-TO) from an official source, with a specific verb ('consultar') and resource (Cadastro). It distinguishes from siblings by emphasizing it is a data consultation from official Brazilian sources, not related to authentication or marketplace 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?

It explains when to use: to consult official public data, with an explicit disclaimer that it is not confidential, and notes it is hosted by the platform with pay-per-query using prepaid credits. It doesn't explicitly contrast with siblings, but the context of official data consultation is clear.

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 beyond annotations by detailing execution semantics: invoke runs tools even when not installed, requires credentials/payment will return links, writes need owner/admin, and search/describe flag installation state. No contradiction with annotations (readOnlyHint=false, openWorldHint=true).

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 large paragraph packed with details, making it dense and harder to scan. It is comprehensive but not front-loaded or segmented; a structured breakdown (e.g., bullet points by action) would improve readability without losing 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?

Given the tool's complexity (multi-action, 23 params, no output schema), the description is remarkably complete: it covers all major flows, usage distinctions, permission requirements, auth/payment links, and even the separate prompt library sub-feature. It provides enough context for the agent to operate effectively.

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 coverage is 0% and there are 23 parameters, the description explains the key action-specific parameters (action, mcp_id, tool_id, arguments, query) through the flow narrative. It also covers prompt library actions, but leaves many parameters (limit, conversation, prompt_vars, etc.) implicit to the schema, so it doesn't fully compensate for the low coverage.

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 this is the official marketplace for MCPs, covering searching, describing, invoking, and installing tools, as well as prompt library actions. It distinguishes from sibling tools (authenticate, cro_to_cadastro_consultar, etc.) by positioning itself as the central catalog and execution layer.

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 the core flow (search -> describe -> invoke), when to use invoke vs install (one-off vs permanent), and mentions subscribe/cancel for billing. Also notes when credentials or payment links are needed and that writes require owner/admin, providing clear decision guidance for the agent.

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 idempotentHint=true but no readOnlyHint or destructiveHint. The description doesn't add much behavioral context beyond implying it sends data. It doesn't contradict annotations. The tool likely just sends feedback, but no mention of response or side effects. With annotations present, the description adds minimal value.

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 short and front-loaded with the main purpose. It's a single sentence plus a second sentence for reproduction guidance. No wasted words, but it could include more structural detail if needed.

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 low schema coverage and no output schema, the description is insufficient. It doesn't explain what happens after reporting, or the format of the conversation parameter, or whether context is optional. The complexity is moderate, but the description leaves many gaps 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 description coverage is 0%, and the description only mentions the conversation array but does not explain the 'message' or 'context' parameters. The description adds some meaning for 'conversation' but leaves the primary 'message' parameter unexplained beyond the overall purpose. It fails to compensate for low schema coverage.

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 reports bugs, missing features, or feedback, and mentions including the conversation array for reproduction. It is clear enough to distinguish from siblings, though it doesn't explicitly differentiate from similar reporting 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 implies when to use it (when reporting issues) but doesn't provide explicit guidance on when not to use it or alternative tools. It mentions including the conversation array, which hints at usage, but lacks explicit context 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds no additional behavioral context such as output format, potential side effects, or prerequisites. It is accurate and non-contradictory but offers no extra transparency beyond 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, front-loaded sentence that conveys the tool's function without any fluff. Every word contributes to meaning, achieving perfect conciseness and 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?

For a zero-parameter, read-only version-inquiry tool with no output schema requirement, the description is fully complete. There are no additional fields or behaviors that need elaboration; the description adequately fulfills the tool's informational need.

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 schema coverage is 100% (vacuously). Per the rubric, 0 params earns a baseline of 4. The description doesn't need to add parameter meaning, and none is missing given the absence of inputs.

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 clear verb (Show) and specifies the resource (MCP platform and adapter versions), making the tool's purpose obvious. However, it does not distinguish itself from siblings like 'toolkit_info' which might also surface version information, so it lacks explicit differentiation.

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 its usage context (checking versions) but provides no explicit when-to-use-when-not-to-use guidance or mention of alternatives. Sibling tool names suggest distinct purposes, but without any exclusionary language, the usage context is only implied, not stated.

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 safety is clear. The description adds value by detailing the return contents (installed MCPs, connection status, accounts, catalog tool counts), which is especially helpful since there is no output schema. No 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?

A single sentence that is front-loaded with the primary verb and subject, then efficiently lists the return items with a colon and comma-separated list. Every word contributes to understanding; 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 state inspection tool, the description fully covers what the agent needs: what the tool returns and the scope of that return. No output schema exists, but the description compensates by enumerating the components of the toolkit state.

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 has no obligation to explain them. The baseline for no parameters is 4, and the description correctly focuses on the return value rather than nonexistent inputs.

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') with a clearly defined resource ('current toolkit state') and enumerates the exact contents (installed MCPs, connection status, connected accounts, catalog tool counts). This distinguishes it from siblings like show_version, which would focus on 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 ('when you need the current toolkit state') but does not explicitly state when to use it vs alternatives, nor mention exclusions. There is no guidance on whether this should be called before authenticate/connect or how it relates to show_version.

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