CPlug (ConnectPlug)

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

Annotations indicate idempotent, non-destructive, and not read-only. The description adds context about the login flow, the two usage modes, and that calling with no args returns a link. It does not contradict annotations and provides useful behavioral details beyond the structured data, though it stops short of describing response handling or 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 three sentences, front-loaded with the purpose, and structured to clearly separate permanent vs. session options. It is a bit dense but every sentence adds necessary information, so it earns a 4 rather than a 5.

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 (one optional parameter, no output schema), the description covers usage, parameter semantics, and alternatives. It does not mention return values or error scenarios, but those are not critical for an authentication tool. The description is sufficiently complete 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 schema has one parameter 'token' with no description, and schema coverage is 0%. The description fully compensates by explaining the token is a JWT, how to pass it in the call, and that omitting the argument triggers a link response. This goes well beyond the bare 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: to authenticate to the MCP server by logging in through the browser and obtaining an access token. It distinguishes itself from siblings by explicitly covering authentication flow, including both permanent (config header) and session-only (token parameter) 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?

The description provides explicit guidance on when to use each approach: adding the token to server config for a permanent connection vs. pasting it for session-only login. It also explains calling with no args to retrieve the login link. However, it does not explicitly mention alternatives or when not to use this tool, so it falls 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?

The description adds valuable behavioral context beyond the annotations (readOnlyHint, idempotentHint): it explains the return structure in two distinct states, including specific fields like 'authenticated:true', 'pending[]', and 'connect_url'. This goes beyond the basic safety hints, though it does not cover all potential states (e.g., partial connectivity), leaving some gaps.

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 concise sentences, front-loaded with the main purpose. Each sentence adds distinct information: the core function, the full-connected state, and the missing-credentials state. There is no verbosity 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?

For a simple tool with no parameters and strong annotations, the description is mostly complete. It explains the return values for two key scenarios but omits possible partial-connection states. Given the simplicity and lack of an output schema, the description is adequate, though slightly more detail on edge cases would improve completeness.

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 the schema is fully covered with no properties. No additional parameter semantics are 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's purpose: 'Returns connection status and URLs.' It uses a specific verb and resource, distinguishing itself from siblings like 'authenticate' by focusing on status rather than action. However, it does not explicitly name sibling tools or contrast with them, so it falls short of a 5.

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 by describing scenarios ('When all providers are connected', 'When credentials are missing'), but it does not explicitly state when to prefer this over alternatives such as 'authenticate'. There is no direct guidance on exclusions or alternative selection, making the usage context implied rather than 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?

Discloses non-obvious behaviors: invoke works even when the MCP is not installed and runs a one-off without bloating the toolkit; auth and payment edge cases are described with connect/checkout links and retry logic; writes require workspace owner/admin; publish_prompt returns a shareable login-free link. These go well beyond the annotation flags and have no contradictions.

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 long but every sentence adds distinct value, structured into core flow, key caveats, usage guidance, permissions, and prompt library. It is front-loaded with the primary purpose and uses clear signal words like 'KEY' and 'prefer'.

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 discovery, execution, installation vs one-off, auth, billing, permissions, and the prompt library in sufficient detail. There is no output schema, but the description explains what key actions return (e.g., connect/checkout links, shareable prompt links, full MCP profiles), making it complete for a complex multi-action 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?

The description effectively explains the core parameters (action, query, mcp_id, tool_id, arguments) through the flow and examples, and references prompt_vars/prompt_slug via the prompt-library actions. However, with 23 parameters and zero schema descriptions, it does not detail several action-specific parameters (cancel_reason, tier_slug, immediate, prompt_category, request_details, etc.), so an agent would need to infer some 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 explicitly identifies the tool as 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them' and details the core flow from search to describe to invoke. It clearly distinguishes the marketplace's broad role from narrower sibling tools.

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?

Offers explicit when-to guidance: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT'. It also explains each action's purpose (list_tools, subscribe/cancel, report_bug, request_mcp) and contrasts the prompt library vs MCP catalog with clear action paths.

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 state idempotentHint=true and destructiveHint=false, covering safety. The description adds that the conversation is used for reproduction, which is helpful context. However, it does not disclose what happens to the report (e.g., whether it is persisted or sent externally), and it 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 a single, efficient sentence that conveys both purpose and a critical usage instruction. There is no redundancy or filler; 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 three parameters, no output schema, and zero schema descriptions, the description is too sparse. It fails to clarify the semantics of two parameters and does not describe any response or follow-up behavior. The explicit mention of the conversation array is helpful but insufficient for fully correct invocation.

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 the conversation parameter (calling it an 'array' even though the schema type is string, which could mislead), but it does not explain 'message' or 'context.' The agent would have to guess what to put in these fields, especially since only 'message' 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 uses the specific verb 'Report' and defines three concrete resources: bug, missing feature, and feedback. It clearly distinguishes this tool from sibling tools like authenticate and marketplace, which serve entirely 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 when to use this tool (when a bug, missing feature, or feedback is needed) and provides a key instruction: include the conversation array for reproduction. While it does not explicitly mention alternatives or exclusions, it is clear enough given that no sibling tools overlap with this functionality.

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 provides only surface-level action descriptions without disclosing potential side effects, especially for the invoke action which executes a tool and may be mutating or require authentication. All annotations are false, so they provide no safety context. The description fails to convey any behavioral traits beyond the basic action outputs.

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 exceptionally concise—three sentences, each covering one action, with no fluff or redundancy. The opening phrase 'Single entrypoint for MCP catalog' immediately establishes context, and the action= format is consistent 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?

Given the tool's complexity (7 parameters, multi-action, no output schema), the description is far from complete. It does not describe return formats (e.g., what fields are returned for search), parameter combinations for each action, error handling, or side-effect warnings. It provides only a minimal overview that leaves many operational details ambiguous.

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, the description must explain parameters, but it only clarifies the 'action' enum values. Other parameters like query, queries, tool_id, arguments, min_score, and force_reindex are left unexplained. Even tool_id is only implied for describe/invoke rather than explicitly tied to those 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 this as the single entrypoint for the MCP catalog and specifies three distinct actions (search, describe, invoke) with their immediate effects. This differentiates it from sibling tools like authenticate and marketplace, making its purpose 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 implies usage context by calling itself the 'single entrypoint' for catalog operations, which suggests it should be used for all catalog-related tasks. It lists the available actions but does not explicitly state when not to use it or mention alternatives, though sibling tools are clearly unrelated in scope.

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 extra behavioral context (e.g., return format, rate limits), but it also does not contradict annotations. For a simple read-only tool, this is adequate but not enhanced.

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 fronts the main action and objects. No wasted words, 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?

With zero parameters, rich annotations covering safety, and no output schema, the description is fully sufficient for an agent to select and invoke this tool correctly. No missing information.

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 adds no parameter-specific meaning, but none is needed since the schema is empty and the functionality is fully described.

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 ('show') and names the exact resource ('MCP platform and adapter versions'). It clearly distinguishes from sibling tools like authenticate or search_tools, 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 usage when version information is needed, but it does not explicitly state when to use it versus alternatives. However, siblings do not overlap with versioning, so the context is clear enough but lacks explicit exclusion 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. The description adds useful context by specifying the returned data (installed MCPs, connection status, accounts, catalog tool counts). It does not mention any side effects, but annotations cover the safety profile, and the description aligns with 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, well-structured sentence that efficiently conveys all essential information without wasted words. It is front-loaded with the action ('Returns') and provides a clear list of what is included.

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 (no parameters, no output schema), the description is complete. It explains what the tool returns and is sufficient for an agent to know when to call it. The sibling context helps situate it among related tools, and the description fully fulfills the informational need.

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 doesn't need to explain parameter semantics because there are none. Schema coverage is 100% (vacuously), and no additional parameter information is necessary.

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 ('Returns') and resource ('current toolkit state'), enumerating the exact contents (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from siblings like show_version, which likely only returns 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 provides clear context: use this to obtain an overview of the toolkit's state. It doesn't explicitly mention alternatives or when-not-to-use scenarios, but for a read-only informational tool, the usage is self-evident and doesn't require exclusions.

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