Conselho Regional de Odontologia GO: Cadastro

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

Annotations declare readOnlyHint=false and idempotentHint=true, meaning the tool mutates state but is safe to repeat. The description adds behavioral details: it sets up an authentication session and distinguishes between permanent (config header) and session-only (token argument) connections. It doesn't specify the exact side effects or output, but the mutation nature is clear and consistent with the description.

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 three sentences long and packs essential information: workflow (log in, copy token), two usage modes, and a recommendation (config header for permanent connection). It's slightly verbose due to the parenthetical { token: "<jwt>" }, but every sentence adds value and there is no 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?

The tool covers its primary use case (authentication) with clear instructions and alternative modes. It doesn't specify the exact response structure or error handling, but for an auth tool, this is acceptable given the annotations (idempotent, non-destructive). The description is sufficient for an agent to know when and how to call it, and what the link-based flow is.

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 one parameter 'token' with no description, so schema coverage is 0%. However, the tool description fully explains the token's purpose: it's the JWT obtained from the browser, used for session-only login. The description also clarifies that the parameter is optional (no args to get link). This effectively compensates for the missing schema description.

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 IDE agent. It specifies the exact action (log in, copy token) and provides two usage modes: permanent via config header or session-only via token argument. The verb 'authenticate' is unambiguous, and the scope (MCP.AI for IDE agents) is defined.

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 step-by-step instructions: log in, copy the access token, and either add it as a header to the config for a permanent connection or paste it as the { token } argument for a session. It also states that calling with no args returns the login link, covering all invocation scenarios.

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 significant behavioral context beyond the annotations (readOnlyHint, idempotentHint). It details exact return values under different conditions (all connected vs. missing credentials), which is valuable and not captured by annotations. It also notes the inclusion of connect_url and per-install URLs, enriching transparency.

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: two sentences, with the primary purpose in the first sentence and conditional details in the second. No redundant or filler content; every sentence adds meaningful 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 lack of an output schema, the description covers the main return scenarios (all connected vs. missing credentials), but it does not mention partial connection states or the exact structure of 'pending' and 'connect_url'. While adequate for a simple status tool, it could be more thorough in explaining edge cases.

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 coverage is trivially 100%. As per the rubric, with 0 params the baseline is 4. The description does not need to elaborate on parameters since none exist.

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: it returns connection status and URLs. It uses a specific verb (returns) and names the resource (connection status and URLs). It distinguishes from siblings like 'authenticate' by describing a status-check behavior, not an authentication action.

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 checking connection status but does not explicitly state when to use this tool versus alternatives like 'authenticate'. No when-not or alternative references are provided, so it relies on the reader to infer the appropriate context.

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 readOnly/idempotent/non-destructive annotations, the description discloses the payment requirement, lack of platform credentials, official/public nature of the data, and LGPD controller responsibilities. This adds meaningful behavioral context and does not contradict any 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 front-loaded with the tool's purpose and uses four compact sentences, each covering a relevant aspect: purpose, access/payment, data source/sensitivity, and legal responsibility. No sentence is wasted.

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 one-parameter read-only lookup with rich annotations, the description is complete: it specifies the source, access requirements, cost model, data sensitivity, and legal context. The absence of an output schema is acceptable because the tool is a simple query and no return-value contract is defined.

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 a single required string `inscricao` with 0% description coverage, and the description does not explain the expected format, source, or example value. The domain context implies it is the CRO-GO registration number, but the description itself adds no explicit parameter-level 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 identifies the tool as a query ('consulta') of CRO-GO ('Conselho Regional de Odontologia GO') registration data from an official source. This is specific and distinct from the generic sibling tools like authenticate, marketplace, and report_bug.

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 clear usage context: hosted by the platform, no platform credentials required, pay-as-you-go with prepaid credits, and data is the same public information available to citizens. It does not explicitly state when not to use it or name an alternative query tool, but the sibling set contains no comparable lookup 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 only say readOnlyHint=false, openWorldHint=true, destructive=false; the description adds substantial behavioral context: invoke runs uninstalled MCPs one-off without bloating the toolkit, returns connect/checkout links when credentials or payment are needed, flags installed_in_toolkit vs installed_in_workspace, and notes auth requirements. 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 dense and every sentence adds meaningful information about a complex multi-action tool. It is front-loaded with the core identity and flow, then covers edge cases and permissions. Its main weakness is being a single long paragraph rather than using structured sections or bullets, but the length is justified by the tool's complexity.

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 (14 actions, 23 params, no output schema), the description covers the main capability flow, one-off invocation behavior, credential/payment failure modes, install-vs-invoke tradeoff, billing actions, prompt library, and permission requirements. It lacks explicit return-value structures and full parameter documentation, but is otherwise remarkably 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?

With 0% schema description coverage and 23 parameters, the description carries a heavy burden. It explains several key params semantically (action, mcp_id, tool_id, prompt_slug, prompt_body, prompt_vars) and the overall flow. However, many params are left unexplained: limit, query, immediate, tier_slug, conversation, cancel_reason, cancel_comment, prompt_targets, report_context, request_details, prompt_category, prompt_description.

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 this as the mcp.ai marketplace and capability/search/execution hub, with a concrete core flow: search → describe → invoke. It distinguishes itself from siblings by explaining that it finds and runs MCPs on demand, rather than being a specific tool like cro_go_cadastro_consultar or a generic report_bug utility.

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: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use.' It also clarifies when to use search, describe, invoke, list_tools, subscribe/cancel, report_bug, request_mcp, and prompt-related actions, plus mentions that writes require workspace 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 convey that the operation is non-read-only, non-destructive, and idempotent. The description adds the useful context that conversation messages aid reproduction, but does not disclose what happens after reporting, whether a response is returned, or potential side effects. 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?

Two sentences with no filler. The key purpose is front-loaded, and the only additional instruction is concise and directly actionable.

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 reporting tool with annotations and no output schema, the description is adequate but has gaps: it does not describe the required message parameter beyond general purpose, explain the context parameter, or indicate what happens after submission. Still, the reproduction hint adds meaningful context.

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 the three parameters. It adds meaning to the conversation parameter by explaining it should contain recent messages for reproduction, but leaves message and context parameters implicit and does not clarify the expected JSON-array-as-string 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 with a specific verb ('Report') and a defined set of resources: bug, missing feature, and feedback. It is easily distinguished from unrelated sibling tools like authenticate, connect, and show_version.

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 for when to use the tool ('Report a bug, missing feature, or send feedback') and provides an explicit instruction to include the conversation array for reproduction. It does not mention alternatives or exclusions, but no competing reporting tool exists among siblings.

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 fully disclose the safety profile. The description adds no extra behavioral context (e.g., no network calls, no side effects), but for a trivial read-only version check, this is sufficient. 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, clear sentence that states exactly what the tool does with no filler. Front-loaded and efficient.

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 read-only, parameterless version tool with comprehensive annotations, the description is fully adequate. No output schema is present, but the return value (version strings) is implicit and well-understood.

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 of 4 applies. The description does not need to explain parameter semantics since there are none, and the schema has 100% coverage (empty properties).

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 verb 'Show' and resource 'current MCP platform and adapter versions' clearly specify the tool's function. It is unambiguous and distinct from sibling tools like authenticate or connect, which serve 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 inherently indicates when to use this tool: whenever version information is needed. With no parameters or alternatives implied, it is self-explanatory and requires no exclusions or comparisons.

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 safety profile is covered. The description adds return-value details but does not disclose additional behavioral traits such as whether data is live or cached, whether credentials are exposed in the response, or whether connection checks have side effects. 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, front-loaded sentence with no filler. It leads with the verb and resource, then uses a colon-separated list to efficiently communicate the return contents. Every word adds value.

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?

With no output schema, the description carries the full burden of explaining the return value, and it does so comprehensively by naming the categories of information returned. The tool has no parameters and safe read-only annotations, so no additional operational context is necessary for an agent to invoke it 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 input schema has zero parameters, so the description does not need to explain parameter semantics. The baseline for a zero-parameter tool is 4, and the description correctly focuses on output content instead of input fields.

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 bounded resource ('current toolkit state') and enumerates exactly what is included: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly distinguishes it from read-only siblings like show_version and from mutating tools like connect or authenticate.

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 the tool should be used when the agent needs an overview of toolkit state, but it does not explicitly state when to prefer this over show_version or other siblings, nor does it provide any exclusions. Since sibling tools exist and could overlap, clearer usage guidance would improve the score.

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