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

Annotations are minimal (readOnlyHint=false, openWorldHint=true), so the description carries the full burden — and it delivers. It discloses non-obvious behaviors: invoke executes one-off runs without installing or 'bloating the tool list,' returns a connect link for credential needs, returns a checkout/top-up link for empty wallets, and flags that writes require workspace owner/admin. These side-effect and prerequisite disclosures go well beyond what annotations 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 content is front-loaded and every sentence earns its place — there is no filler. However, the entire description is one dense run-on paragraph exceeding 400 words, with no section breaks, bullets, or per-action headers despite covering 14 actions and 23 params. The information density is high but the lack of structure makes it hard for an agent to scan quickly.

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 extreme complexity (23 params, 14 actions, no output schema, no required params), the description covers the core flow, the invoke/install distinction, auth/payment behaviors, permission requirements, and the prompt library comprehensively. Residual gaps: per-action return shapes (what search actually returns beyond installed flags, what invoke's success response looks like) are not specified, forcing the agent to infer response contracts. Still, it is unusually complete for a tool this sprawling.

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 coverage over 23 parameters, the description must compensate. It explains the central action enum exhaustively, covers mcp_id/tool_id/arguments through the flow narrative, describes the prompt-library params (prompt_vars as {{variables}}, shareable slug links), and cancel params via billing context. However, several params remain undocumented in both schema and description: immediate, tier_slug, conversation, limit, report_context, and request_details. The description does heavy lifting but leaves roughly a third of the params unexplained.

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 a specific, unambiguous statement — 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them' — and enumerates the 14 distinct actions it dispatches. It clearly differentiates from siblings: report_bug, list_tools, and request_mcp are positioned as separate facets, and the marketplace's role as catalog+runner is distinct from tools like authenticate or 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?

Provides explicit when-to-use guidance: 'prefer invoke for a single/occasional use' versus 'Use install only to make an MCP PERMANENT in the active toolkit,' plus 'request_mcp asks us to build a NEW MCP when nothing fits.' The core flow is laid out step-by-step (search → describe → invoke), and billing actions (subscribe/cancel) and prompt-library actions are given clear contexts. This is textbook usage scoping with named alternatives.

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