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

The description discloses key side effects and preconditions: invoke runs one-off without installing, returns connect link if credentials needed, returns checkout link if wallet empty, and writes require workspace owner/admin. This goes beyond the annotations (readOnlyHint=false) and clarifies mutation, auth, and payment behavior. No contradiction with 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 dense single block but logically flows from definition to core flow to key caveats to other actions to prompt library. Every sentence adds useful info for a tool with 23 parameters and 14 action values. However, it is long and could be split into structured bullets for readability, so not a 5.

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?

Despite no output schema, the description explains return behavior for critical actions (describe returns full MCP profiles with params/pricing/auth, invoke returns connect/checkout links, get_prompt returns full text with variables filled). It covers auth, billing, installation semantics, and the prompt library. For a tool representing an entire marketplace, it is nearly 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 description coverage, the description compensates well for core parameters: action is explained through the flow (search→describe→invoke), mcp_id/tool_id/arguments are contextualized ('pick the right tool_id', 'invoke RUNS that tool'). Prompting parameters are named. However, some parameters (limit, immediate, tier_slug, conversation, cancel_reason, etc.) remain undocumented, leaving gaps.

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 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' This gives a specific noun (marketplace) and clear verbs (catalog, run). It enumerates distinct actions (search, describe, invoke, install, etc.) that differentiate it from siblings like authenticate or connect.

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?

Explicit guidance is provided: 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT'; also says 'invoke works even when the MCP is NOT installed'. Each sub-action (report_bug, request_mcp, subscribe/cancel, list_tools, search_prompts) has a one-line when-to-use statement.

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