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

The description discloses many behaviors not in annotations: invoke works even when the MCP is not installed and avoids bloating the tool list; credential/payment failures yield connect or checkout links with a retry instruction; writes require workspace owner/admin; search/describe flag installation state; publish_prompt returns a shareable no-login link. No contradiction with readOnlyHint=false or destructiveHint=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 well structured: it front-loads the core search→describe→invoke flow, highlights the key invoke behavior, then distinguishes install vs invoke, lists auxiliary actions, states permission requirements, and covers the prompt library. Every sentence adds useful information for a 14-action, 23-parameter tool, so the length is justified.

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 high-complexity tool with no output schema, the description covers the central workflows, edge cases (credentials, payment, permissions), and the prompt-library subdomain well. It falls short on some details: the 'resume' action is never mentioned, and exact output shapes for search/describe/list_tools are not specified, though the description does say what key actions return.

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 carry the parameter burden. It does explain the action enum values and the roles of mcp_id, tool_id, arguments, prompt_vars, and prompt_slug through the described workflows. However, several parameters such as immediate, tier_slug, conversation, report_context, and request_name are not individually addressed, so it is not fully compensated.

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 by identifying the tool as 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them', then explains the core search→describe→invoke flow and the separate prompt library. This clearly states what the tool does and distinguishes it from siblings like openfinance_* 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?

It gives explicit when-to-use guidance: use search for capability requests, describe to inspect one MCP, invoke for one-off runs, install only for permanent toolkit membership, list_tools for currently callable tools, and request_mcp when nothing fits. It also says 'prefer invoke for a single/occasional use' and names alternatives, which is exactly what this dimension asks for.

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