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

Surfaces critical runtime behaviors beyond annotations: invoke works even if the MCP is not installed, returns a connect link when credentials are needed, and returns a checkout/top-up link when the wallet is empty. It also discloses that writes (install/uninstall/subscribe/cancel and one-off install behind invoke) require workspace owner/admin. These details go well beyond the mere readOnlyHint/openWorldHint/destructiveHint flags, enabling the agent to anticipate side effects and auth failures.

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 the tool has 14 actions and significant auth/edge-case semantics, so the length is mostly earned. It is front-loaded with the core identity, then flows into action logic and prompt library. A more structured bulleted format would improve scannability, but the density is justified and there is no filler.

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 and thin annotations, the description covers all major workflows: discovering MCPs, running one-off invokes, handling credential/payment interruptions, permanent installation, workspace auth requirements, prompt library usage, and the fallback request_mcp path. It tells the agent exactly what to expect and how to retry, making the tool self-contained for the common cases.

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 coverage, the description carries the full burden and does so well by explaining the action enum values (search/describe/invoke/list_tools/request_mcp/prompt actions) and interpreting key params like tool_id ('you pick the right tool_id'), arguments (passed to invoke), and prompt_vars (filled in get_prompt). It does not explicitly describe every optional parameter (limit, immediate, tier_slug, cancel_reason, etc.), but the workflow narratives make the main parameter relationships clear.

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', immediately stating the tool's central purpose. It clearly differentiates marketplace from siblings by enumerating its unique capabilities (search/describe/invoke/install/prompt library) and positions it as the hub for discovering and executing MCPs, rather than a single-purpose tool.

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 explicit selection guidance: 'prefer invoke for a single/occasional use' vs 'use install only to make an MCP PERMANENT', and 'request_mcp asks us to build a NEW MCP when nothing fits'. It also explains the core flow (search→describe→invoke) and when to use list_tools, giving the agent clear decision rules for when to choose this tool and which action within it.

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