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

Even with annotations, the description adds meaningful behavioral context: invoke runs MCPs even when not installed, does not bloat the tool list, may return connect or checkout links, and install makes tools permanently available. Permission and login requirements are disclosed accurately, and nothing contradicts the 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 long, but it is front-loaded, procedural, and dense with useful information rather than filler. The core flow, distinctions between invoke/install, payment/credential behavior, permissions, and the prompt-library subsection are logically organized, though heavier structure or bullets would make the 23-parameter surface easier to scan.

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?

Given a complex dispatcher-style tool, no output schema, and no parameter descriptions, the description covers the primary flows, auth/payment outcomes, permission constraints, and the prompt library surprisingly well. Minor gaps remain, such as resume, immediate, tier_slug, and detailed cancellation/report parameter behavior, but the overall tool context is complete enough for an agent to act effectively.

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 23 parameters with 0% description coverage, so the tool description carries the responsibility, and it does much of that work: action values, mcp_id, tool_id, arguments, query, and prompt fields are given real semantics through the core flow and prompt-library explanation. Some parameters remain opaque (e.g., immediate, tier_slug, cancel_reason, prompt_targets), which keeps this from a 5, but the description compensates well for the bare schema.

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 defines the marketplace as the central MCP catalog and execution surface, with explicit verbs for each capability: search, describe, install, uninstall, subscribe, cancel, list_tools, request_mcp, and the prompt-library actions. It distinguishes the marketplace from sibling tools by making its resource (catalog + runner + prompt library) concrete and by outlining a core flow rather than just restating the name.

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?

Provides exceptionally explicit usage guidance: prefer invoke for one-off use, use install only for permanent toolkit membership, use request_mcp when nothing fits, and use list_tools to see what is callable now. It also notes that write actions require workspace owner/admin privileges and that credential/payment failures map to connect/checkout links before retrying.

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