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

The description goes well beyond annotations, which only state readOnlyHint=false and destructiveHint=false. It discloses that invoke works without installation, returns connect links for credential-driven tools and checkout links for paid tools when the wallet is empty, requiring a retry. It also notes permission requirements ('Writes ... require workspace owner/admin') and the distinction between installed_in_toolkit vs installed_in_workspace. This is rich behavioral context not captured in 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 (~450 words) but densely informative and logically organized: it starts with the core flow, then dives into the invoke vs install distinction, covers other actions, and ends with the separate prompt library. Each sentence earns its place; however, the undifferentiated wall of text could benefit from bullet points or section headers to improve scanability, though the content justifies the length.

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?

The description thoroughly explains the tool's behavior, including one-off invocation, authentication/payment handling, permission requirements, and the prompt library. But it fails to provide any mapping between the 23 parameters and the actions, which is critical for actual usage. Given the complexity and lack of an output schema, the description is incomplete because it leaves the parameter layer entirely unaddressed.

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 23 parameters and 0% schema description coverage, the description must compensate by explaining how to use the parameters, but it does not. It mentions actions (search, describe, invoke, etc.) but never maps them to parameter names like query, mcp_id, tool_id, arguments, or limit. The agent has no idea how to populate the schema or what each parameter does, making the tool very hard to invoke correctly despite the excellent behavioral prose.

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 the tool's purpose: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It enumerates the core flow (search → describe → invoke) and distinguishes itself from siblings like authenticate and connect, which are separate concerns. The verb is specific and the resource (MCPs/prompts) is unambiguous.

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?

The description provides explicit guidance on when to use each action: 'Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile... invoke RUNS that tool.' It contrasts invoke vs install: 'prefer invoke for a single/occasional use. Use install only to make an MCP PERMANENT.' It also covers when to use subscribe/cancel, report_bug, request_mcp, and the prompt library endpoints. There is clear exclusion guidance (e.g., 'without adding the MCP to the toolkit') and permission requirements for writes.

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