Conselho Federal de Medicina: Cadastro

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

Annotations indicate idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description adds that the config-header approach gives a 'permanent, non-expiring connection' while pasting a token is 'session-only', and that no-args returns a link. This discloses side-effect and persistence behavior beyond what annotations convey. It doesn't contradict too few details to impact the score.

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 run-on sentence with multiple instructions and a trailing colon, making it less scannable than ideal. It packs several ideas (IDE mention, browser flow, config path, session path, call syntax). It is fairly compact but could be restructured into bullet points or shorter sentences for better readability. Still, it is not bloated enough to drop below a 3.

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 basic parameters, the description covers both authentication modes, explains the session vs permanent distinction, and gives the exact invocation contract. It omits details like error handling or logout procedures, but such information may be outside the tool's current scope. Given the tool's simplicity, this 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?

With 0% schema coverage and one optional parameter, the description fully explains 'token': 'call with { token: "<jwt>" } after the user pastes' and distinguishes the no-args case to obtain the login link. This compensates for the schema's silent field, adding meaningful semantics. A small deduction for not elaborating the token's format JWT can be inferred.

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 handles authentication ('log in in the browser, copy the access token') and provides two distinct usage modes (permanent via config header or session-only via token). While the verb+object are clear, it slightly obscures purpose by mixing instructions for IDE agents with end-user workflow. It does not explicitly contrast with the sibling 'connect' tool, but the auth role is 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 explicitly offers alternatives: 'Best: add it to this server's config ...' versus 'Or paste it here for a session-only login', and specifies exact call patterns: 'call with { token: "<jwt>" } ... or with no args to get the link.' This gives an agent direct guidance on when to use which approach, meeting the rubric's 'when/when-not/alternatives' at the highest level.

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 valuable behavioral context beyond annotations: it states no platform credentials are needed, there is a per-query cost, the data is non-confidential, and the client is responsible for legal compliance under LGPD. It aligns with the readOnlyHint and does not contradict any annotation.

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 repeats 'consulta' and 'fonte oficial' multiple times and includes legal jargon. It could be more streamlined, but it is not excessively 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 does not elaborate on the output format or fields returned, nor does it mention error scenarios or rate limits. While it covers payment and legal aspects, the lack of output schema or description leaves a significant gap for users to understand what data the tool returns.

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 schema provides no descriptions, and the description does not explain the meaning of 'uf', 'nome', or 'inscricao'. Without any hints, users cannot infer what these fields represent (e.g., state, name, registration number). The description adds no clarity to the 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 clearly states that the tool performs a query (consulta) for registration data from the official Brazilian Federal Council of Medicine. It distinguishes itself from sibling tools by focusing on medical registry lookups, mentioning the official source and the prepaid credit model.

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 mentioning 'consulta em fonte oficial' and 'pague por consulta com crédito pré-pago', indicating a paid query service. It does not explicitly contrast with alternatives but gives sufficient context that this tool is for fetching registration data, not for authentication or general platform operations.

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. The description adds behavioral detail by specifying the exact return fields (authenticated, pending[], connect_url) and conditional logic, which enriches understanding beyond the annotations 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 two sentences, front-loaded with the main purpose, and efficiently explains the two possible outcomes. Every word earns its place with 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?

For a simple, parameterless, read-only tool with no output schema, the description fully explains the return values and their conditions. It is complete for the agent's needs and matches the tool's simplicity.

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 there is nothing for the description to add beyond the schema. Baseline per rubric is 4 for 0 params, and the description appropriately focuses on behavior rather than 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 clearly states it 'Returns connection status and URLs,' which is a specific verb+resource. It distinguishes from siblings like authenticate by focusing on status/URLs, and the conditional behavior further clarifies its purpose.

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 clear context on when to use (check connection status) and describes conditional outcomes based on credential state. However, it doesn't explicitly mention alternatives or when not to use, so it stops 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?

It clearly discloses that invoke runs uninstalled MCPs without bloating the toolkit, returns connect and checkout/top-up links under auth/payment constraints, and requires workspace owner/admin for mutating actions. This adds substantial behavioral context beyond the sparse annotations and is not contradicted by readOnlyHint=false.

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 but front-loaded, starting with identity and then moving through the core flow and key differences between invoke and install. It earns most of its sentences, but one very long unbroken paragraph makes it harder to scan, and phrases like 'pontualmente (one-off)' are slightly redundant.

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 high complexity, absent output schema, and zero parameter documentation, this description is unusually thorough: it covers auth, install-state flags, billing links, prompt-library behavior, and the canonical discovery flow. Still, it does not describe return formats for list_tools/search results or the meaning of resume, immediate, tier_slug, and several prompt/cancel parameters.

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 23 parameters and 0% schema coverage, the description helps by explaining the action enum and the main flow around mcp_id and tool_id. However, it leaves many parameters unexplained, such as arguments, immediate, tier_slug, conversation, prompt_vars, cancel_reason, cancel_comment, and the more specialized prompt fields, so it only partially compensates for the schema's missing descriptions.

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 defines 'marketplace' as the official mcp.ai catalog and execution layer, with specific verbs and a core search→describe→invoke flow. It does not just restate the name, but the tool is really a multi-purpose action router (discovery, installs, billing, prompts) rather than a single-purpose verb+resource, so it loses a point for sharpness.

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 strong in-tool guidance: prefer invoke for one-off use, use install only to make MCPs permanent, use request_mcp when nothing fits, and use the prompt-library actions for prompt text instead of MCPs. However, it never distinguishes between its own report_bug action and the sibling report_bug tool, or says when connect/authenticate should be used instead.

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 annotation 'idempotentHint: true' is present, and the description does not contradict it. The description adds behavioral context by explaining that the tool is for reporting and that the conversation array is needed for reproduction. No annotations contradict 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 two sentences, concise and front-loaded with the core purpose. Every word is useful, and it avoids 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 that the tool is fairly simple with 3 parameters and no output schema, the description is mostly complete. It covers the main use case and the key parameter (conversation). It might benefit from mentioning that 'context' is optional, but overall 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?

Schema description coverage is 0%, but the description mentions the 'conversation' parameter explicitly, implying its purpose. However, it doesn't explain 'context' or 'message' beyond the schema, and the 'message' parameter is essentially self-explanatory. The description adds some value but not comprehensive 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 clearly states the tool's purpose: report a bug, missing feature, or send feedback, and includes instruction to include conversation array for reproduction. This is specific and distinguishes it from sibling tools like marketplace or toolkit_info, 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 provides clear guidance on when to use the tool (to report a bug or provide feedback) and instructs to include the conversation array for reproduction. It implicitly excludes use for other purposes, and while it doesn't explicitly mention alternatives, the context is clear enough given the sibling list.

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 readOnlyHint, idempotentHint, and destructiveHint. The description adds no new behavioral details, such as return format or failure modes, but it is consistent with 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 a single, concise sentence with no redundant wording, perfectly sized for the tool's simplicity.

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 adequately conveys what the tool returns (versions) without needing an output schema. Minor details like exact format are omitted, but the essence is complete for a simple getter.

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?

There are no parameters in the schema, so there is nothing to explain. The description does not need to add parameter meaning beyond the empty schema.

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 is specific and distinct from sibling tools, which are unrelated to version retrieval.

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 simple getter tool has no parameters, and the description implicitly conveys when to use it (when version info is needed). No explicit alternatives exist, but the context 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?

The description fully discloses the read-only nature of the tool by stating it 'returns' state, and the annotations (readOnlyHint: true, idempotentHint: true) align perfectly. No contradiction; it is clearly an informational query with no 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 a single, concise sentence that lists all key aspects without unnecessary verbosity. It effectively communicates the tool's purpose and output in a compact form.

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 info tool with no parameters and no output schema, the description fully covers what it does and what it returns. It may not mention authentication prerequisites, but given the sibling tools, it's likely intended to be called after setup, and the description itself is self-contained.

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 there are no parameter descriptions to worry about. The description focuses on the return value, specifying exactly what fields are provided, which serves as the complete semantic specification.

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 is explicit and complete: it states what the tool returns (toolkit state) and enumerates the four specific components it includes (installed MCPs, connection status, accounts, catalog tool counts). This leaves no ambiguity about the tool's purpose.

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 indicates the tool is for retrieving informational state, but it does not explicitly state when to use it (e.g., after connecting tools or to diagnose issues). However, the sibling tools (authenticate, connect) imply a typical workflow where this would be called post-setup.

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