The whole registry in numbers

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

The annotations already cover safety, idempotency and open-world behavior, and the description adds context that the annotations cannot: the data comes from a latest daily run (freshness), it is instant and takes no input (latency and call cost), and it returns a few kilobytes of JSON (payload size). The only minor gap is that it does not say how stale the daily snapshot can be or whether anything is paginated, although the output schema covers the return shape.

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?

It is a single front-loaded paragraph: the core definition opens it, the routing guidance follows, and operational facts close it. The middle section is a long enumeration of aggregate categories. All of it is informative, but it reads slightly like a brochure list rather than a prioritized summary.

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 definition covers all the essentials: what it aggregates, the freshness of the source data, that it needs no input, its speed and payload size, and which sibling tool to use for other shapes of query. The return structure is deferred to the output schema, so nothing an agent needs in order to call this correctly is missing.

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 tool has zero parameters, so the baseline is 4, and the description reinforces this with "no input." There is nothing further to document on the parameter side.

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 uses a specific verb ("aggregates") and resource ("the board's latest daily run over the whole official MCP registry") and then enumerates the concrete aggregate families: availability, token-cost percentiles, auth, protocol versions, transports, heaviest servers and publishers. This is enough to distinguish it from lookup_server and search_servers 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 gives two explicit use conditions (the registry as a whole, or as the baseline to compare a single server against) and names the sibling alternatives with their roles: search_servers for a ranked list, lookup_server for one server. When and when-not are both covered.

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