diagnose_instance

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

With no annotations, the description carries the load and does well: it discloses that Java version checks depend on a running bridge-enabled Prism and that the report explicitly states when checks were skipped, which prevents the agent misreading a partial result as a clean pass. It does not mention whether probing is slow or what the response looks like, so it falls short of full transparency.

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 sentences, front-loaded with the purpose and followed by the one behavior that changes the outcome. The parenthetical about the Java path and probed version is density, not padding; every clause earns its place.

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 annotations and no output schema, the description must stand alone, and it does name the three things resolved plus the issues/warnings report. What remains unstated is the shape of that report (severity levels, whether failures abort or are advisory), which matters for an agent deciding what to do with the result.

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 single parameter 'id' has 0% schema description coverage, so the description must compensate. It refers to 'an instance' but never states whether id is an instance id or a display name, or how it relates to the identifiers used by get_instance or launch_instance.

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 states a precise verb and scope: a launch-readiness check that resolves effective Java (path plus probed version), the required Java major for the instance's Minecraft version, and memory settings, then reports issues and warnings. That is clearly distinguishable from sibling operations like launch_instance, get_instance_status, and get_instance.

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?

Usage is implied by 'launch-readiness check' (run it before launching), but no sibling is named as an alternative and no explicit when/when-not rule is given. The one real condition it does spell out is the bridge-enabled Prism prerequisite for Java probing, with the fallback behavior when that is absent.

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