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

With no annotations, the description carries the full burden and does substantial work: it discloses that the report is cached, free, will not return 402, performs no re-probe, and enumerates body fields (cache.presenceStale, cache.callabilityStale, refresh.priceUsd/network/rest.url). It stops short of explaining what 'presenceStale'/'callabilityStale' actually mean for the caller.

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?

Front-loaded with the key fact (cached, free) and tightly written with no filler. The telegraphic fragments ('Does not 402', 'mcp.tool refresh_host') are dense and slightly cryptic, but each clause carries real information.

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 one-parameter, no-annotation, no-output-schema tool, the description covers the operation, its cost/side-effect profile, the alternative to use for live data, and the shape of the returned body. The main gap is semantic meaning of the staleness flags, which the agent must infer.

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 the single 'domain' parameter (normalization, label/length rules, rejection cases) is already fully documented in the schema. The description adds nothing about the parameter, so the baseline 3 is correct.

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 identifies the resource precisely as a cached host report and explicitly contrasts it with the live-probe sibling refresh_host ('Does not re-probe'), so an agent can distinguish it from refresh_host/refresh_host_protocol without opening the schema. It lacks a clean verb ('lookup' must be inferred from the name), which keeps it short of a 5.

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 signals when this tool is the right pick ('Cached... Free. Does not 402. Does not re-probe') and points at the alternative for the live case ('refresh (payable live re-probe... mcp.tool refresh_host)'). There is no explicit 'when-not' phrasing, but the cached-vs-payable routing is clear enough that the agent can choose between siblings.

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