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

The description discloses critical non-obvious behavior far beyond the annotations: invoke runs tools even when not installed and without bloating the tool list, missing credentials yield a connect link, empty wallets yield a checkout/top-up link with retry semantics, and install/uninstall/subscribe/cancel require privileged roles. It adds rich context that the generic annotations (readOnlyHint=false, destructiveHint=false) cannot convey.

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 very long, dense single paragraph with no paragraph breaks or bullet structure, making it hard to scan despite every sentence carrying real content. It is appropriately sized for the tool's complexity, but the wall-of-text format and the appended prompt-library section hurt readability.

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 tool with 14 actions, 23 parameters, no output schema, and no schema descriptions, the description covers the main flows, auth/permission requirements, billing edge cases, retry behavior, installed-state flags, and the prompt library. Gaps remain — the 'resume' action is never mentioned, return-value behavior per action is unspecified, and several parameters lack context — but for this scope it is remarkably 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 and 23 parameters, the description carries the full burden and compensates well for the core flow: it explains how mcp_id, tool_id, action, and arguments relate to search/describe/invoke, and describes prompt-related parameters (prompt_slug, prompt_vars, prompt_body) in the prompt-library section. However, several parameters (limit, query, immediate, tier_slug, cancel_reason, conversation, report_context, prompt_targets, etc.) remain unexplained, so compensation is strong but incomplete.

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 identifies a specific resource — the mcp.ai marketplace — and names its distinct verbs: discover (search/describe), run (invoke), make permanent (install), manage billing (subscribe/cancel), and handle prompts. It clearly differentiates this tool from siblings by defining its scope as the in-platform catalog and runner for MCPs. No ambiguity about what this tool does.

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 an explicit core flow (search → describe → invoke), contrasts install vs invoke with a clear preference ('Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use'), and routes sub-actions (list_tools, report_bug, request_mcp, subscribe/cancel) with their purposes. It even states who may perform writes (owner/admin). This is exemplary routing guidance.

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