Conselho Federal de Medicina Veterinária: Cadastro

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

Annotations already show idempotent and non-destructive, and the description adds useful context: the two mechanisms (config header vs session token), the non-expiring nature of the config method, and that calling with no args returns a login link. 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?

Two sentences pack all essential information: the login flow, permanent vs session options, and the parameter usage. Front-loaded with the primary purpose and minimal waste.

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 one optional parameter and no output schema, the description covers all necessary aspects: the two login methods, how to obtain the token, and the recommendation for permanent setup. It's complete for its scope.

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 optional 'token' parameter with zero description coverage. The description fully explains it by showing the exact call format with a JWT and when to use it (after user paste), and also explains the no-argument case. This compensates completely for the schema's lack of detail.

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: authenticating IDE agents via a browser login and token capture. It distinguishes from the sibling 'connect' tool by specifying it's for MCP.AI IDE agents and describes both permanent and session-based login methods.

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 gives explicit usage scenarios: for permanent access, add the token to server config; for session-only, pass the token or call with no args to get a link. While it doesn't explicitly name alternatives or when-not-to-use, the guidance is clear and context-rich.

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), the description adds context about credential requirements and payment model, and clarifies that data is not confidential. However, it does not disclose potential side effects, error behavior, or rate limits, leaving some behavioral aspects unexplained.

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 redundant phrases (e.g., repeating 'official sources') and legal boilerplate. It is structured into a few sentences, but could be tightened without losing essential 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?

The description lacks key practical details: it does not explain what the response contains, how to construct a valid query, or what each parameter means. It covers legal and operational context but misses crucial usage information that would make the tool self-explanatory.

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 includes parameters like `uf`, `query`, and `tipo_inscricao`, but the description gives no explanation of their meaning or expected values. Without any hints, the agent cannot infer how to populate these fields correctly.

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 tool queries information from official Brazilian sources, specifically for CFMV registration data. It distinguishes itself from generic siblings by hinting at the specific domain (veterinary medicine council), though it could be more explicit about the exact data returned.

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 mentions operational aspects like lack of platform credentials and prepaid payment, but it does not explicitly state when to use this tool versus alternatives. It provides no direct guidance on appropriate use cases or prerequisites beyond legal disclaimers.

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 readOnly, idempotent, and non-destructive behavior, so the bar is lower. The description adds concrete details about return values (authenticated flag, connect_url) and conditions, enhancing transparency without contradicting 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 sentences, tightly packed with relevant information. It avoids redundant phrasing, explains key states, and is well-structured for quick parsing. No unnecessary words 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?

Given the simplicity of the tool (no parameters, read-only operation), the description sufficiently covers its behavior and expected return values. It mentions 'per-install URLs' which could be slightly ambiguous, but that's a minor gap and does not impact overall completeness in typical usage contexts.

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 100% by default. The description does not need to elaborate on parameters. Per the rubric, a baseline of 3 is appropriate for high schema coverage with no parameter info, and no additional explanation is required.

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, distinguishing it from siblings like 'authenticate' which likely performs actual authentication. It specifies the exact outcome for connected and missing credentials scenarios, leaving no ambiguity about its function.

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 the tool (to check connection status) and provides expected outcomes under different conditions (all connected vs. missing credentials). While it doesn't explicitly contrast with alternatives, the context is clear enough for an agent to decide when to invoke 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 declare readOnlyHint=false (writes possible) and the description aligns, explicitly stating 'Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin.' No contradiction. Beyond annotations, it discloses rich behavioral context: auth flow ('if the MCP needs a credential/login, invoke returns a connect link'), payment flow ('if it is paid and the wallet is empty, invoke returns a checkout/top-up link'), the one-off execution trait ('without bloating the tool list'), and prompt-library share links 'that opens without login.'

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 dense wall of text — no bullets, no action-by-action breakdown — making it hard to parse despite containing valuable content. Every sentence does earn its place given the tool's 14-action, billing/auth/prompt-library scope, so length is arguably justified, but the total lack of structural organization hurts scannability for an agent.

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 highly complex tool (23 params, 14 actions, billing, auth, prompt library, permissions) with no output schema, the description is quite complete: it covers all actions, the recommended flow, auth and payment edge cases, ownership requirements, and the one-off vs permanent distinction. It falls slightly short of 5 because it does not describe return payload shapes, and with no output schema the agent must infer response formats on its own.

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 across 23 parameters, the description must compensate heavily, and it does substantially. It implicitly documents all 14 action enum values by narrating each action's purpose in the flow. It covers the prompt-related params (search_prompts, get_prompt with {{variables}}, publish_prompt with shareable slug). However, it does not systematically map every parameter (arguments, immediate, tier_slug, conversation, request_name, prompt_targets) to its role, leaving some params under-explained despite the verbose text.

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 role: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It specifies a concrete resource (the mcp.ai catalog) and the actions it performs (search, describe, install, invoke, subscribe, prompt library). It distinguishes itself from siblings like authenticate, connect, and toolkit_info by establishing itself as the marketplace/catalog/runtime hub.

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?

Exceptionally explicit about when to use each action: 'Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile... so you pick the right tool_id → invoke RUNS that tool.' It gives clear decision rules: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use' and 'list_tools lists what is callable right now.' It also covers when to use report_bug, request_mcp, subscribe/cancel, and the prompt library functions, plus a permission caveat for writes.

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 provided: readOnlyHint=false, destructiveHint=false, idempotentHint=true. The description doesn't contradict these. It adds that the conversation array should be included for reproduction, which is a behavioral expectation. However, it doesn't disclose what happens after reporting (e.g., does it send a message, create a ticket, etc.) or any side effects. With annotations covering basic safety, the description adds some context but could be richer.

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 primary purpose. It directly instructs on an important usage detail (including conversation). No wasted words. It earns a high score for brevity and 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?

Given the tool complexity is low (3 params, simple types, no output schema), the description is adequate for a reporting tool. It tells the user what to include (conversation) and what the tool is for. However, it doesn't specify the format of 'conversation' or what happens after submission, which could affect expectations. The annotations provide some context like idempotentHint=true, but the description could be more complete about the expected 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 description coverage is 0%, and the description does not explain the parameters beyond mentioning 'conversation array' in relation to reproduction. It fails to clarify the meaning of 'context' and how 'conversation' should be structured. The parameter 'message' is required but its content is not elaborated. This is a significant gap: the description must compensate for low schema coverage, but it only covers one of three 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 the tool's purpose: 'Report a bug, missing feature, or send feedback.' It identifies the verb (report/send) and resource (bug/feature/feedback). It distinguishes from siblings like show_version and toolkit_info which are informational, while this is for reporting issues. However, it doesn't explicitly differentiate from marketplace or connect, but the context is clear enough.

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 bugs, missing features, or feedback) but provides no explicit guidance on when not to use it or alternatives. It does give an instruction to include 'conversation array with recent messages for reproduction,' which is a usage hint. However, it lacks clear exclusions or comparison with sibling tools.

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, idempotentHint, and destructiveHint, covering the safety profile. The description adds no additional behavioral context (e.g., whether output is formatted, or network calls are made). It is consistent with annotations but does not enrich them.

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, clear sentence with no redundant words. It is front-loaded and directly states the tool's function.

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, and existing annotations, the description is sufficient to inform the agent about the tool's primary behavior. It does not explain return value format, but that is not required given no output schema and the trivial nature of the task.

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 is 4. The description does not need to explain parameter details since none exist, and the schema is fully covered (100% of zero 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 the verb 'Show' and the specific resource 'current MCP platform and adapter versions,' making the tool's purpose immediately understood. It is distinct from sibling tools like authenticate or connect, which involve actions rather than version queries.

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?

No guidance is provided on when to use this tool versus alternatives. While the simplicity of the tool reduces the need for extensive context, there is no explicit statement about when to invoke it (e.g., 'Use to check compatibility or report version-related issues').

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, idempotentHint, and destructiveHint, so the description adds value by detailing the returned state contents (MCPs, statuses, accounts, catalog tools). This provides context beyond the safety profile, though it does not describe side effects—consistent with read-only.

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 direct and efficient, front-loading the purpose and enumerating contents without any 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 low complexity (no params, no output schema), the description fully explains what the tool returns, including specific details about MCP state, connection status, accounts, and catalog tool counts. Annotations cover safety, making this complete for an agent.

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?

No parameters exist, so the description adds no parameter-specific meaning. Per rubric, 0 parameters yields a baseline of 4, and the description adequately describes what the tool does without needing to clarify parameter usage.

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') with an enumerated list of contents (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from sibling tools like show_version and 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 usage for checking toolkit state but does not explicitly state when to use it vs. alternatives or provide exclusions. It offers clear context but lacks explicit guidance on use cases or non-use cases.

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