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

The description carries a heavy transparency burden beyond the sparse annotations (readOnlyHint=false, destructiveHint=false) and fully delivers. It discloses that invoke runs one-off without installing, that writes require workspace owner/admin, that credential needs surface as connect links, and that empty wallets trigger checkout links. No contradiction with annotations; instead it enriches them with permission scoping and side-effect semantics.

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?

Every sentence earns its place and the most important info is front-loaded, but the entire description is one dense, unbroken paragraph with no visual structure — no bullets, line breaks, or section headers separating the marketplace flow from the prompt library. For a tool with 14 actions and 23 params, this density hurts scannability even though nothing is wasted. Adequate but poorly organized.

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 (23 params, 14 actions, no output schema), the description covers remarkably much: full action taxonomy, install-vs-invoke tradeoffs, permission requirements, billing/credential handling, and installed_in_toolkit vs installed_in_workspace flags. It describes notable return products (connect links, checkout links, shareable mcp.ai/p/<slug> links). Minor gaps: it does not describe return structures for search/describe or list_tools results, which the absent output schema leaves unexplained, keeping it one point below a 5.

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 across 23 parameters, the description must compensate significantly. It adds meaning to the critical action parameter by enumerating all 14 behaviors and explains the functional role of tool_id and mcp_id in the describe/invoke flow, plus prompt_vars in get_prompt. However, many parameters (conversation, cancel_comment, report_context, prompt_targets, immediate, tier_slug) receive no semantic explanation, leaving gaps for an already undocumented schema. Partially compensates but not fully.

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 precise statement: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It defines the core search→describe→invoke flow and differentiates from siblings by naming alternatives (authenticate, connect) implicitly through its marketplace scope. Even though it also covers the prompt library sub-domain, the primary purpose is unmistakably stated.

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?

Extensive explicit guidance is provided: the core flow ('action=search discovers MCPs by intent → describe returns one MCP's full profile... → invoke RUNS that tool'), explicit when-not guidance ('prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT in the active toolkit'), and when list_tools is appropriate ('lists what is callable right now'). It even handles edge cases like connect links and checkout/top-up retry flows, giving the agent clear decision criteria.

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