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

The description discloses rich behavior beyond the annotations: invoke works even when the MCP is not installed (one-off, no toolkit bloat), returns connect links for auth needs and checkout links for empty wallets with a retry flow, and writes require workspace owner/admin. Search/describe flag installed status. The readOnlyHint=false annotation aligns with the documented mutating actions - no contradiction.

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, run-on wall of text with no bullets, section breaks, or paragraph separation between the core marketplace behavior and the prompt library subsection. Every sentence carries useful information, so nothing is wasted, but scanability suffers badly for a tool with 14 action modes; the structure does not match the tool's complexity.

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 having no output schema and a massive scope (14 actions, 23 params, 0% param coverage), the description covers the end-to-end flows: search→describe→invoke, connect/checkout link returns with retry, install-vs-invoke permanence, admin requirements, and what describe/invoke/publish return (profile with tool_id+params+pricing+auth, links, shareable slug). Only a clear output/return structure is missing, which the prose partially mitigates.

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 carries the full burden and substantially compensates: it explains the action enum (all 14 values), the tool_id+arguments relationship for invoke, mcp_id for describe/install, and the prompt library params (prompt_slug, prompt_body, prompt_vars, prompt_title, prompt_targets, prompt_category, prompt_description). However, several params (limit, query, message, conversation, immediate, tier_slug, cancel_reason/comment, report_context, request_name/details) are only implied or omitted, so it doesn't fully cover all 23.

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 this is the official mcp.ai marketplace - the in-platform catalog plus the way to run them, covering capability requests. It precisely defines the dispatch role via the action parameter (search/describe/invoke/install/etc.), which distinguishes it from single-purpose siblings like authenticate, connect, and toolkit_info. The verb+resource+scope is specific and unambiguous.

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 when-to-use guidance throughout: the core flow is spelled out (search discovers → describe returns profile → invoke runs), with direct preference statements like 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT.' It also covers when to use list_tools, subscribe/cancel, report_bug, request_mcp, and the prompt library actions, plus owner/admin requirements for writes and the retry-after-link flow.

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