instance_ping

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

Annotations declare readOnlyHint=true, and the description adds the key behavioral distinction that this performs a live probe rather than reading cached state, which matters for latency and failure modes. It stops short of saying what a failed ping looks like or whether it can time out.

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?

Two short sentences, zero filler, with the primary action front-loaded and the disambiguation following. Every clause carries routing or scope 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 single-parameter read-only probe, the description covers what it does, how it differs from neighbors, and that the result is live. What a ping result contains (latency, success/failure) is left implicit since there is no output schema to lean on.

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?

One required parameter at 100% schema coverage, so the schema already defines hostname as 'Instance hostname'. The description's 'by hostname' restates the same idea and adds no format or resolution detail beyond the schema, making the baseline 3 appropriate.

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 ('ping'), scope ('one instance') and mode ('live by hostname'), which immediately separates it from the bulk and read-only siblings. An agent can pick this without opening any 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?

Explicitly names two alternatives and the condition selecting each: instances_ping_all for every instance, instance_get for the stored record without pinging. The remaining case (live single-instance probe) is the implied default and is unambiguous.

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