Conselho Regional de Odontologia PI: Cadastro

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

Describes side effects like permanent config modification vs session-only, and mentions browser interaction. Annotations indicate idempotent and non-destructive, which the description aligns with. No contradictions, but it doesn't detail error handling or exact response 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 somewhat verbose but still concise and logically structured. It efficiently conveys multiple usage modes without unnecessary filler.

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?

Covers the tool's purpose, usage patterns, and parameter meaning. It doesn't explain return values, but with no output schema that's not required. Overall it provides enough context for an agent to use it 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?

The description fully explains the 'token' parameter, noting it's a JWT and how to use it (pass it or omit to get a link). Even though schema coverage is 0%, the description compensates entirely.

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 this tool is for authentication, mentioning browser login and token handling. It distinguishes from siblings by focusing on auth, though it doesn't explicitly compare to the 'connect' tool.

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 usage instructions: adding token to server config for permanent auth, or passing token for session-only, and calling with no args to get a login link. This gives clear when-to-use guidance for each scenario.

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 annotations already declare the operation read-only, idempotent, and non-destructive. The description adds valuable behavioral context by explaining the two main return states: all connected versus credentials missing. Since there is no output schema, these return-state disclosures are especially useful.

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 only two sentences and each one adds substantive information. The main purpose is front-loaded, and the conditional outcomes are stated 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?

For a zero-parameter, read-only, low-complexity tool, the description is complete: it states what the tool returns, the successful connected state, and the missing-credentials state. The absence of an output schema is sufficiently compensated by the explicit return-state examples.

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 an empty object, so there are no parameter semantics for the description to enhance. The 0-parameter baseline applies, and the description correctly avoids inventing any parameter guidance.

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 starts with a specific verb and resource: it returns connection status and associated URLs. The conditional details about authenticated:true and pending[] clearly define what the tool exposes, distinguishing it from action-oriented sibling tools like authenticate 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?

The description implies that this tool is for checking connection status and obtaining connect_url for unauthenticated credentials, but it does not explicitly say when to prefer it over sibling tools such as authenticate. It gives clear conditional behavior but no direct guidance on choosing alternatives 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 annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses additional behavioral traits such as the platform-based hosting without credentials, prepaid credit payment per query, and the nature of data (not confidential). It also clarifies LGPD compliance and the client's data controller role, which adds meaningful transparency without contradicting 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 core purpose in the first clause, followed by supplementary details on payment, data sensitivity, and legal obligations. While it is slightly verbose, each sentence adds context, and there is no irrelevant filler. The structure is logical and easy to parse.

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 contextual aspects like payment, data source, and legal requirements, but it omits specifics about the input parameter and expected output (no output schema exists). It gives a general sense of what the tool does but lacks enough detail to fully guide an agent on how to invoke it correctly, especially regarding the 'inscricao' 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?

The schema has one required parameter 'inscricao' with no description (coverage 0%). The description does not explain what this parameter represents (e.g., it should be the registration number) or its format. Since the description fails to compensate for the lack of schema documentation, it leaves the agent uncertain about the parameter's 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: querying registration information from the Regional Council of Dentistry PI (CRO PI) via an official source. It uses specific language 'Cadastro, consulta em fonte oficial' and distinguishes itself from siblings like authenticate, marketplace, and report_bug, 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 some context (e.g., it queries official Brazilian sources available to citizens) but does not explicitly state when to use this tool versus alternatives, nor does it mention any exclusionary conditions. The usage is implicitly tied to the tool's name and domain, but there is no direct comparison or guidance for when not to use 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 are sparse (readOnlyHint=false, destructiveHint=false), so the description rightly carries the burden and adds real context: writes require workspace owner/admin, invoke returns a connect link if credentials are needed and a checkout/top-up link if the wallet is empty (with retry guidance), and invoke runs one-off without bloating the toolkit. No contradiction with annotations found.

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 information-dense and front-loads the core search→describe→invoke flow before pivoting to the prompt library. But it's a single run-on paragraph with no segmentation, and the length (~300 words) could benefit from grouping by action cluster. The stray 'consulta um CPF' breaks the otherwise English text, and 'resume' in the enum is never elaborated.

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 14 actions, 23 params, and no output schema, the description covers the main discovery, invocation, install, billing, and prompt-library flows comprehensively, plus auth requirements and payment/retry behavior missing from annotations. Minor gaps remain: the resume action is omitted, response/error formats are unaddressed, and there's no guidance on edge cases like list pagination.

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 there are 23 parameters, so the description must compensate. It meaningfully maps the action enum to roles (action=mcp_id/tool_id/arguments for the flow; prompt_slug/prompt_body/prompt_vars for the library), covering the core parameters indirectly. However, many params (limit, message, immediate, tier_slug, cancel_reason, report_context, prompt_targets, prompt_category, request_details) are never tied to their actions, leaving gaps.

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 explicitly states the tool is the mcp.ai marketplace — the catalog of every MCP/tool AND the way to run them. It clearly conveys the multi-action dispatcher nature and distinguishes itself from siblings like authenticate, connect, and toolkit_info by being the catalog/runner of MCPs, with a separate 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?

Excellent when-to-use guidance per action: search discovers by intent, describe returns profiles, invoke runs tools (even uninstalled ones), install makes an MCP permanent, list_tools shows what's callable now, request_mcp is for when nothing fits. It explicitly contrasts 'prefer invoke for a single/occasional use' against 'use install only to make an MCP PERMANENT' — a direct when/not recommendation.

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 and destructiveHint=false, so the description doesn't need to repeat safety. It adds context about including the conversation array for reproduction, which is helpful. However, it doesn't disclose what happens after submission (e.g., confirmation, tracking) or any rate limits.

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, two sentences, and front-loaded with the purpose. It includes a key usage hint (conversation array) without unnecessary 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's simplicity (3 params, no output schema), the description covers the core purpose and a key usage detail. However, it lacks explanation of the 'context' parameter and how the conversation string should be formatted, which could lead to misuse.

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 mentions 'conversation array' but the schema defines 'conversation' as a string (likely JSON), and 'context' is not explained. The description adds minimal meaning beyond the schema's property names.

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: reporting bugs, missing features, or feedback. It specifies the resource (bug/feature/feedback) and the action (report/send). It distinguishes from siblings by focusing on user feedback rather than authentication, connection, or 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 when to use it (when reporting issues or feedback) but does not explicitly state when not to use it or mention alternatives. It provides a hint about including conversation context for reproduction, which is useful but not a full usage guideline.

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, destructiveHint=false, and openWorldHint=false, which clearly indicate this is a safe, read-only operation. The description adds context by specifying that it shows platform and adapter versions, which is useful. Since the annotations cover the safety profile, the description doesn't need to repeat it; however, it could add a note about what the output includes (e.g., version numbers, build info). Given the high annotation coverage, a 4 is appropriate.

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 clear and to the point. It provides the necessary information without any fluff. Every word earns its place.

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 simplicity of the tool (no parameters, no output schema, strong annotations), the description is complete. It clearly states what the tool does. However, it could be more explicit about what the output looks like (e.g., 'returns version strings'), but since there's no output schema, a bit more detail could have been added. Still, for a simple version check, this is 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 the schema coverage is 100% (empty properties). The description doesn't need to explain parameters since there are none. The baseline for zero parameters is 4, and the description doesn't add any information about parameters, which is fine because there's nothing to add.

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: to show current versions of the MCP platform and adapters. This is specific and distinguishes it from siblings like authenticate, marketplace, etc., though it doesn't explicitly contrast with those siblings; the verb 'show' and resource 'versions' are clear.

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: call this tool to see versions. It doesn't explicitly say when to use it versus alternatives, but given that it's a simple informational tool with no parameters and sibling tools like 'toolkit_info' might overlap, some guidance on when to prefer this over 'toolkit_info' would have been helpful. The context is implied but not explicit.

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 safe-read behavior is established. The description adds meaningful context by specifying what data is returned (installed MCPs, connection status, accounts, catalog tool counts), which goes beyond the annotations. It does not mention edge cases or performance characteristics, but the annotation coverage lowers the burden.

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, well-structured sentence that front-loads the action ('Returns the current toolkit state') and then lists the specific components. Every word adds value, with no redundancy or tangential 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 that there is no output schema, the description must convey the return values, and it does by listing the categories of information: installed MCPs, connection status, connected accounts, and catalog tool counts. It is sufficient for an agent to understand what the tool provides, though it does not specify the exact data structure or field names. The low complexity and strong annotations allow this to be 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% (there is nothing to document). Per the rubric, a zero-parameter tool receives a baseline of 4. The description adds no parameter information because none exist, which is 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 uses a specific verb 'Returns' and clearly identifies the resource 'current toolkit state', then enumerates the exact contents (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from sibling tools like show_version or marketplace by focusing on the overall toolkit state rather than a single aspect.

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 by defining the tool's output, but it does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. An agent can infer that this is the tool to call when needing an overview of toolkit status, but no direct comparison or conditional guidance is offered.

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