Server status

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

Annotations already declare readOnly, idempotent, non-destructive, openWorld, so safety is covered. The description adds genuinely new context: the check is 'one small request to Divar' (cost/latency footprint) and it discriminates network failure from argument error. It does not discuss caching/TTL of the reported values, so it stops short of 5.

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 short sentences, front-loaded with what it returns and then the diagnostic condition. The closing pointer to the server instructions is mildly tangential but earns its place as ordering guidance.

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 parameters, no output schema to explain, and rich annotations, the description covers what an agent needs: what is reported, when to call it, and its request cost. Only the shape/reliability of the reported values (e.g. cache freshness) is left implicit.

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 takes no parameters, so there is nothing for the description to clarify beyond the schema; baseline for a zero-param tool is 4.

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?

States a specific verb-and-resource ('Is Divar reachable and how fast') plus the exact facets exposed (version, live latency, caches, local watch state). This clearly separates it from the search/listing siblings, which never report transport health.

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?

Gives an explicit trigger — 'Call first when other tools fail' — and states the diagnostic payoff (distinguishing a blocked network from a bad argument). It also routes the agent to the server instructions for the normal tool order, so when-not-to-use is implied by that ordering.

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