Sanções Canadá (SEMA)

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

Annotations already indicate idempotent, non-destructive behavior. The description adds context about the two operational modes (link generation and session token) and the difference between permanent and session-only connections. 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 informative but somewhat verbose and awkwardly structured, mixing user instructions with tool invocation details. It could be tightened to a clearer, more front-loaded format.

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, it covers the main scenarios (config vs session, token vs no token). It doesn't mention return values or potential errors, but given the simplicity and available annotations, it is largely 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?

The schema provides only a 'token' string with no description (0% coverage), but the description fully explains it as a JWT from the browser and how to use it, adding complete meaning beyond the 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 authenticates to MCP.AI, with specific verbs like 'log in' and explicit resource. It distinguishes from sibling tools by being the only auth tool, though it doesn't name them.

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 clear context for when to call with no args (get link) vs with token (session login), and recommends the config header approach for permanent access. Does not explicitly contrast with alternatives, but the usage modes are well explained.

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 bar is lower. The description adds valuable context about return behavior in different states (authenticated:true vs connect_url), which goes beyond the annotations and helps the agent understand what to expect.

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 every sentence adds meaningful detail about behavior. No wasted 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 tool has no parameters, no output schema, and good annotations, the description covers the two key scenarios (all connected vs credentials missing). It could mention partial connection states or clarify 'pending', but for a low-complexity status tool, the description is largely 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?

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameters, and it does not omit any schema-covered information. No additional parameter semantics 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 the tool returns connection status and URLs, with specific details about two outcomes. It is specific about the resource (connection status) and the action (returns), but does not explicitly differentiate from sibling 'authenticate', so it meets 'clear but no sibling 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 usage as a status-checking tool by describing what it returns under different conditions, but it does not explicitly state when to use this tool versus alternatives like 'authenticate'. The guidance is implicit rather than explicit, with no exclusions or direct 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?

Goes well beyond annotations by revealing that invoke can run uninstalled MCPs without adding to the toolkit, returns connect/checkout links for auth/payment, flags installed status in search/describe, and notes that writes require workspace owner/admin. 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 dense but efficient—every sentence adds value. However, it is a long wall of text that mixes multiple topics (MCP discoverability, invoke semantics, billing, admin requirements, prompt library) without clear breaks, making it harder to parse than necessary.

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 14-action tool with no output schema, the description is quite complete: it covers core flows, invoke vs install, credential/payment handling, admin permissions, and the prompt library. Yet some actions (resume) and many parameters are left unexplained, and return formats are only partially described.

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 params, the description must compensate. It thoroughly explains the action enum values, but most parameters (mcp_id, arguments, limit, cancel_reason, etc.) remain undocumented. It adds meaning to the core flow but not enough to fully map parameters to actions.

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 the official mcp.ai marketplace—the catalog for MCPs/tools and the execution engine. It outlines a specific flow (search → describe → invoke) and distinguishes the prompt library as a separate feature, making it distinct from siblings.

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 when-to-use guidance: prefer invoke for one-off tasks, install for permanent additions; subscribe/cancel for billing, request_mcp for new MCPs, search_prompts for prompt text. It also explains follow-up behavior (connect/checkout links) and admin requirements for writes, offering clear alternatives.

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 readOnlyHint=false and idempotentHint=true; the description adds practical behavioral guidance by instructing to include the conversation array for reproduction. No contradiction exists, and the reporting action is clearly conveyed.

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 concise sentences: first states the purpose, second gives a specific instruction. No redundant information, well front-loaded.

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 tool with good annotations, the description covers the main purpose and usage. It could mention the expected outcome (e.g., ticket created), but that is not critical for a bug-report tool.

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 explicitly mentions the conversation parameter and its purpose, but does not describe the 'context' parameter and only implies that 'message' is the report text. Partial compensation only.

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?

Description uses specific verb 'report' and identifies targets: bug, missing feature, or feedback. It clearly differs from sibling tools like authenticate or connect, which serve unrelated 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?

Description implies when to use it: for bugs, missing features, or feedback. It also instructs to include the conversation array for reproduction. It does not explicitly mention alternatives, but the sibling tools are unrelated, providing clear 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds operational context: no credentials required, pay-per-query cost, and LGPD legal responsibilities for the controller, going beyond the annotations without contradicting 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 composed of three sentences, starting with the core purpose, then providing cost and access details, and finally the legal disclaimer. It is efficient with no redundant phrasing, though the LGPD sentence adds length without directly aiding tool invocation.

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 and annotations cover safety, but the description omits any explanation of the expected return value or the behavior of the 'completo' parameter. Since there is no output schema, these gaps make the description incomplete for an agent needing to interpret results.

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 two parameters with zero description coverage, and the description fails to explain the meaning of 'completo' or explicitly map 'Nome' to the name parameter. This leaves the agent without essential guidance on how to set parameters, especially the optional boolean.

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 checks a name against Canada's international sanctions list (SEMA), using a specific verb and resource. It is distinct from siblings like authenticate, connect, and marketplace, 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 explicitly positions the tool for compliance and AML due diligence, and notes the cost model (prepaid credits) and the public access nature of the data. It does not discuss when not to use this tool or mention alternative sanctions lists, but the context for appropriate use is clearly 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, covering the safety profile. The description adds specificity by clarifying exactly what versions are shown (MCP platform and adapter), which goes beyond the tool name. It does not describe output format or potential errors, but for a simple read-only version tool this is sufficient.

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 directly states the tool's function without any wasted words or redundant details.

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 tool with strong annotation coverage and no output schema, the description is complete. It fully conveys the tool's scope (platform and adapter versions) and is adequate given the simplicity of the operation.

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 baseline is 4. The description correctly adds no parameter information, which is appropriate since there are no parameters to explain.

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 action ('Show') and the specific resource ('current MCP platform and adapter versions'). This distinguishes it from siblings like authenticate, connect, and 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 implies use when version information is needed, but it does not explicitly state when to choose this over alternatives or mention any exclusions. There is no direct comparison with sibling tools like toolkit_info, though the narrow scope ('versions') gives some implicit guidance.

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 the output content (installed MCPs, statuses, accounts, counts), but does not mention potential caveats like whether the data is cached, whether authentication is required, or if there are any rate limits. This is consistent with annotations and provides some extra context.

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 lists exactly what the tool returns. Every phrase earns its place, with no redundancy or 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?

Given the tool's simplicity (zero parameters, no output schema, comprehensive annotations), the description fully specifies the return content. It leaves no ambiguity about what information is provided, and annotations cover behavioral safety. The sibling tools do not reveal any missing contextual aspects.

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 accepts zero parameters, so the schema coverage is trivially 100%. According to the rubric, a baseline of 4 is appropriate for 0-param tools; no parameter documentation is needed beyond the 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 uses the specific verb 'Returns' and details the resource as 'current toolkit state', enumerating four concrete components: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly sets it apart from action-oriented siblings like authenticate/connect and the more generic 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 read-only status-reporting purpose is implied, but the description does not explicitly state when to use this tool versus alternatives such as show_version or when not to use it. No exclusions or alternative tool names are mentioned, leaving usage cues to the agent's inference.

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