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

Beyond the annotations, the description discloses several non-obvious behaviors: invoke runs a tool one-off even when the MCP is not installed, returns a connect link when credentials are needed and a checkout/top-up link when the wallet is empty, requires retry after the user opens the link, carries permission restrictions on writes, and yields shareable prompt-library links that open without login. This is rich behavioral context that annotations alone do not provide.

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 and every clause carries a distinct fact, but it is written as a single run-on paragraph with some mixed-language and garbled artifacts like 'pontualmente' and 'the one-off install behind invoke'. Given the tool's complexity, a more structured or bulleted layout would significantly improve scannability.

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 sweep of the description covers the core flow, the invoke-vs-install distinction, permission requirements, auth/payment edge cases, and the prompt library. However, with 14 actions and 23 parameters and no output schema, several actions like resume, report_bug, list_tools, and request_mcp are not named or explained, and no return-value details are given. It is enough for the main happy path but not for full tool coverage.

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 0% description coverage across 23 parameters, and the description compensates only for the central ones: action values (search, describe, invoke, install, prompt actions), query as intent, mcp_id/tool_id in the flow, and prompt_slug/body for publishing. Most parameters such as arguments, prompt_vars, conversation, immediate, tier_slug, cancel_reason, request_details, and cancel_comment remain unexplained, so the compensation is partial at best.

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 opens with 'official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them' and then details the search→describe→invoke core flow plus the prompt library. It names specific verbs and resources for each mode (search, describe, invoke, install, publish_prompt) and is clearly distinguished from the sibling calculator 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?

The description explicitly routes between actions: 'search discovers MCPs by intent → describe returns one MCP's full profile... → invoke RUNS that tool', and it states 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use'. It also notes that writes require workspace owner/admin. However, it does not explicitly say when to bypass marketplace for already-installed sibling tools, so the alternatives are not fully enumerated.

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