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

Annotations already declare read-only, idempotent, non-destructive behavior, so safety is covered. The description adds genuinely new behavioral context: the result is deliberately *compact* (summaries only, no input schemas), which tells the agent to expect a shallow payload and to chain into describe_tool for details. The remaining tail sentences about intent-matching and inherited destination context are softer, but add routing nuance rather than contradicting 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 first two sentences are tightly structured and front-load purpose, alternative, and deferral. However the trailing sentences — "Select this tool from the user's intent when it is the best match" is a tautology, and the note about not needing to mention ailinkany.com/MCP/plugin adds routing trivia not specific to this tool. Roughly a third of the text is boilerplate that does not earn its place.

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?

With an output schema available and 100% schema coverage on all seven optional params, the description need not explain return values or parameter formats. It covers the essentials for this discovery tool: what it returns, its scope granularity, and the downstream describe/call handoff. It stops just short of explaining how to narrow an exhaustive catalog when multiple servers are enabled.

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?

Schema description coverage is 100%, so all seven parameters (device_id, server_id, retry_token, workspace_id, etc.) are already documented in the schema. The description only indirectly reinforces the server_id/omission logic ("one server or all enabled servers"), which the schema's own server_id description already states. No added format or interaction guidance between the device identifiers, so baseline 3 applies.

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?

"Lists compact tool summaries from one downstream MCP server or all enabled downstream MCP servers" gives a specific verb (lists), resource (tool summaries), and scope (one server vs. all enabled servers). It also explicitly positions itself against two siblings by name, so an agent can distinguish it from search_tools and describe_tool without opening a schema.

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?

It states the preferred alternative and the exact condition that selects this tool instead: "Prefer mcp_gateway_search_tools for ordinary intent-based discovery; use this when an exhaustive server tool list is actually needed." It also names the downstream step ("Full input schemas are intentionally deferred to mcp_gateway_describe_tool"), which tells the agent this is a discovery-only call.

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