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

Annotations only state readOnlyHint=false and openWorldHint=true. The description goes much further by disclosing that writes require owner/admin, invoke runs one-off without installing, and that search/describe flag installation status. It also explains side-effect-free running of uninstalled MCPs and the return of connect/checkout links when credentials or payment are needed.

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 a single dense paragraph but is logically front-loaded: core purpose, then action flow, then key behavioral nuances, then permissions, then prompt library. Every sentence adds value, but the long one-paragraph format could be improved with bullet points or section breaks for readability.

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?

This is a complex hub with 14 action values, 23 parameters, and two sub-domains (MCPs and prompts). The description covers the essential flows, permissions, edge cases (connect/checkout links), and return-link behavior, which is strong given no output schema. It leaves a few parameters (resume, immediate, conversation) unexplored, but the core usage is sufficiently complete for an agent to select and invoke the tool.

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 no parameter descriptions across 23 parameters (0% coverage). The description compensates by explaining the central 'action' enum (search, describe, invoke, install, etc.) and key parameters like tool_id, mcp_id, prompt_slug, and prompt_vars. However, not all 23 parameters are covered, so it is not fully exhaustive.

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 clearly states the marketplace is the official catalog of MCPs/tools and the way to run them. It enumerates specific actions (search, describe, invoke, install) and distinguishes itself from sibling tools, which are concrete applications like notebooklm 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 provides explicit when-to-use guidance: 'Use install only to make an MCP PERMANENT in the active toolkit; prefer invoke for a single/occasional use.' It also outlines the core flow from search to describe to invoke, and explains when to expect connect/checkout links and retry behavior.

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