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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), so the description adds genuine context: 'ok' specifically means initialize and tools/list both succeeded, and this is an automated probe rather than a hands-on test. That distinction materially changes how an agent should interpret results. The `openWorldHint: false` annotation sits slightly awkwardly with a description that implies pulling live data from the official Registry, but this is not a clear contradiction.

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?

Three tightly packed sentences with no filler, and the most important fact (what the dataset is) comes first. The parenthetical defining 'ok' earns its space; the endpoint-equivalence sentence is marginally useful for API-oriented callers.

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 no output schema, the description should say more about the shape of each returned record beyond the check result, and it never explains pagination or how `limit` interacts with the default result filter. It is adequate to identify the dataset but leaves real gaps for a tool whose return value is entirely unspecified.

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 0%, so the description must compensate, and it largely does not. It explains only what the `ok` value of `result` means, saying nothing about `limit`, its 1-200 bounds, or the other enum values (`auth_required`, `http_error`, `error`, `all`). The default of `ok` and the fact that it silently filters the listing are never surfaced.

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 resource: remote MCP servers from the official MCP Registry, paired with Agent Tested's automatic check result. However, it never distinguishes this tool from the very similar sibling `find_working_mcp_servers`, leaving the agent to guess which one to call. There is also internal tension between 'servers that need no auth' and a `result` enum that includes `auth_required`.

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?

No when-to-use or when-not-to-use guidance is given, and no alternative is named despite `find_working_mcp_servers` and `search_tools` being obvious candidates. The only routing hint is the equivalent REST endpoint, which tells an agent how to fetch the same data elsewhere, not when this tool is the right choice.

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