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

Beyond annotations (readOnlyHint=false, openWorldHint=true), the description discloses that invoke runs MCPs even when not installed, a one-off execution without adding to the toolkit. It explicitly states that writes require workspace owner/admin, and details the connect/checkout flow for auth and payment. This adds significant behavioral context not available from annotations.

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 long, unbroken paragraph packed with essential details, but it lacks structured formatting (e.g., bullets, sections). It is concise for the amount of information but repeats concepts like 'one-off' and 'installed_in_toolkit vs workspace' multiple times, slightly reducing 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?

For a tool with 23 optional parameters, 14 actions, no output schema, and minimal annotations, the description is remarkably complete. It covers the full workflow (search→describe→invoke), distinguishes install vs invoke, handles auth/payment edge cases, lists all subcommands (subscribe, cancel, report_bug, request_mcp, prompt operations), and explains the prompt library separately.

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, the description must explain parameters. It explains the action enum values in context (e.g., 'action=search discovers MCPs by intent', 'invoke RUNS that tool'), and mentions tool_id and arguments implicitly. It covers most key parameters but does not individually detail limit, immediate, tier_slug, or prompt_* parameters; however, the action-level guidance compensates for the majority.

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 is explicit: it defines the marketplace as the official catalog of MCPs/tools and the way to run them, covering both discovery and execution. It lists all major actions (search, describe, install, invoke, etc.) and distinguishes from sibling tools by stating report_bug sends feedback and that it also hosts a prompt library separate from MCPs.

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 provides concrete guidance on when to use invoke vs install ('prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT'), explains how to handle credential/payment scenarios (connect/checkout links), and clarifies that list_tools shows what is callable right now. It also notes that search/describe flag installed status, guiding discovery.

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