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

With only sparse annotations (readOnlyHint=false, idempotentHint=false), the description adds meaningful behavioral detail: invoke runs the tool one-off without adding the MCP to the toolkit, writes require workspace owner/admin, invoke may return connect/checkout links, and prompt share links open without login. It does not disclose all side effects of subscribe/cancel/resume or rate limits, but it provides substantial context beyond 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 dense: nearly every sentence adds a distinct fact about search/describe/invoke, install-vs-invoke, auth requirements, or the prompt library. It is front-loaded with the core purpose and flow, though the single-paragraph structure makes it harder to scan than a bulleted breakdown would be.

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 14-action, 23-parameter tool with no output schema and minimal annotations, the description covers the main lifecycle and edge cases well, including auth, payment, and one-off execution. Still, it omits the return shapes for search, list_tools, install, subscribe, and request_mcp, and does not clarify the semantics of parameters like immediate, resume, or conversation, which are important for correct invocation.

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 zero property descriptions, so the description must carry the parameter-semantics burden; it does a solid job for the central parameters by explaining the action enum, the importance of tool_id for invoke, and how prompt_vars/prompt_slug fit into get_prompt/publish_prompt. However, with 23 parameters, several remain only inferable from their names (immediate, conversation, prompt_targets, report_context), so it is not fully compensating for the 0% schema coverage.

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 identifies the tool as 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' and explains the core search → describe → invoke flow. It is unambiguous about the overall resource and scope, though it does not explicitly differentiate itself from sibling tools like report_bug or connect, and it also bundles the prompt-library feature into the same 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?

The description gives explicit when-to-use guidance: 'prefer invoke for a single/occasional use' versus 'Use install only to make an MCP PERMANENT', names request_mcp for cases where nothing fits, and explains the retry pattern when invoke returns a connect or checkout link. This is strong, actionable guidance that distinguishes between the many actions the tool can perform.

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