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

No contradiction with annotations (readOnlyHint:false aligns with documented writes; openWorldHint:true aligns with a dynamic catalog). The description adds substantial behavioral detail beyond annotations: invoke runs tools one-off 'even when the MCP is NOT installed' without bloating the toolkit, returns connect/checkout links for auth/payment with retry semantics, requires 'workspace owner/admin' for writes, and flags installed_in_toolkit vs installed_in_workspace in search/describe. Minor unaddressed behaviors (resume semantics, subscribe details) hold it slightly below 5.

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 carries genuine information — no filler — and the core flow is front-loaded at the start. However, it is a single dense ~350-word wall of text covering both MCP marketplace and the prompt-library sub-system, with no bullets, sections, or action-by-action structure. An agent parsing the action×parameter matrix only telegraphically references each parameter, which hurts scannability despite the density.

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 23-parameter, 14-action dual-purpose tool with no output schema, the description covers the core search/describe/invoke flow, the one-off invocation caveat, permission requirements, and connect/checkout edge cases admirably. Gaps remain: several actions are only listed by name (resume, subscribe/cancel mechanics, list_tools return contents), and parameters like immediate, tier_slug, conversation, and prompt_targets are never explained. Substantial but incomplete documentation for the tool's true complexity.

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?

Schema description coverage is 0% across 23 parameters, so the description carries full burden — but it only clarifies action, mcp_id, tool_id, and arguments conceptually. The remaining 15+ parameters (limit, query, immediate, tier_slug, prompt_body, prompt_vars, conversation, request_details, cancel_reason, prompt_targets, etc.) are never mentioned or mapped to the described flows. With 23 undocumented parameters and zero schema descriptions, the description fails to compensate for the coverage gap.

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 states the purpose precisely: 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It explains the core search→describe→invoke flow and differentiates from sibling tools by noting it 'carries the mcp.ai PROMPT LIBRARY' separately, and single-action siblings like report_bug appear as sub-actions here. The verb+resource+scope are all explicit and highly specific.

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?

Excellent guidance: 'Core flow: action=search discovers MCPs by intent → describe returns... → invoke RUNS that tool.' It explicitly contrasts invoke vs install ('Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use'), explains the connect/checkout retry flow ('the user opens it, then you retry'), and directs when to use request_mcp ('asks us to build a NEW MCP when nothing fits'). Explicit when/alternatives and exclusions are all present.

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