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

Annotations are minimal (readOnlyHint=false, openWorldHint=true), so the description carries the burden. It discloses that invoke runs MCPs temporarily without bloating the toolkit, that it may return connect/checkout links requiring user action, and that writes require permissions. It also notes that search/describe flag installed status. Slight gap: does not disclose that actions can have side effects beyond writes (e.g., subscribe/cancel) and lacks explicit rate limits/timeouts.

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 single dense paragraph with no headers or bullet points, mixing multiple concepts (MCP marketplace, prompt library, billing, permissions) and detailed flow explanations. While it is information-rich, it is not front-loaded or scannable; it takes repeated reading to extract key rules. It could be split into sections (e.g., Overview, Key Actions, Permissions, Prompts) for better usability.

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 the tool's complexity (14 actions, 23 parameters, no output schema, no nested objects), the description covers the core flow, key actions, triggered links, permissions, and the prompt library with enough detail for an agent to select and invoke actions correctly. It also addresses when to prefer invoke over install and mentions the prompt library's purpose, which is essential for this multifaceted tool.

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 schema_description_coverage=0% and 23 parameters all optional, the description must compensate. It explains the roles of key parameters implicitly (action, mcp_id, tool_id, arguments, prompt_* fields) by describing the flow (search, describe, invoke, prompt library), but does not map each parameter to its specific usage. Yet the enumeration of actions and narrative helps agents infer parameter meanings, providing above-baseline compensation.

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 that this tool is the official marketplace for discovering, describing, invoking, and managing MCPs, as well as a prompt library. It distinguishes itself from siblings by being the central hub for MCP discovery and execution, but the broad scope (14 actions) makes the primary purpose diffuse; a clearer 'verb+resource' would be 'access the marketplace to search, describe, invoke, and manage MCPs and prompts'.

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?

Explicitly explains when to use each action: use 'invoke' for one-off runs even if not installed, use 'install' for permanent addition, and mentions capabilities like searching, describing, and billing. It also provides clear alternatives to siblings (e.g., 'report_bug' for feedback, 'request_mcp' for building new ones) and specifies that writes require workspace owner/admin permissions.

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