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

Beyond annotations (readOnlyHint=false, openWorldHint=true), the description reveals critical non-obvious behavior: 'invoke works even when the MCP is NOT installed — it runs the tool one-off without adding the MCP to the toolkit or bloating the tool list.' It discloses the auth redirect link, the wallet/checkout fallback, admin permission requirements for writes, and the no-login requirement for prompt links. This goes well beyond what the annotations convey.

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 description is information-dense, but it is a single wall of uninterrupted prose with no paragraph breaks, lists, or visual anchors — a challenge for a tool with 14 actions and a prompt library. The numbered flow arrows (→) help, as does semicolon-delimited enumeration, but a long description of this scope would benefit from structuring. Adequate but not polished.

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 an extremely complex tool (14 actions, 23 params, no output schema), the description covers the core end-to-end flows (discover→describe→invoke), error/recovery paths (connect link, checkout link, retry), permission model, and even the return shape of publish_prompt (shareable mcp.ai/p/<slug> link). Minor gaps: no detail on search/list_tools result structures or subscribe tier semantics, but for the complexity involved this is notably complete.

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 and 23 params, the description carries full burden and largely delivers: it explains the action enum dispatch (all 14 values), mcp_id/tool_id/arguments flow, and the prompt_* param family. However, several params get no treatment (cancel_reason enum, conversation, request_*, report_context, query, limit, immediate, tier_slug), leaving the agent to infer their roles. Strong compensation for the core flow, incomplete on the long tail.

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+resource pattern: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It clearly differentiates from siblings by owning the full catalog domain (search/describe/install/invoke) versus siblings like authenticate, connect, and show_version. The catalog-vs-prompt-library duality is explicitly flagged, leaving no ambiguity about what this tool does.

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?

Pair-anchored justifications are explicit: 'Use install only to make an MCP PERMANENT' vs 'prefer invoke for a single/occasional use.' The description provides a full decision flow ('action=search discovers MCPs by intent → describe returns one MCP's full profile...'), states when invoke needs a retry ('the user opens it, then you retry'), and clarifies admin requirements for writes. This is exemplary when-to-use-vs-alternatives guidance.

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