emu_get_healthz

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

With no annotations, the description alone must carry behavior disclosure, but two words disclose nothing: no statement about side effects, no confirmation this is a read-only operation, no response format details. The only implicit signal is that 'get' plus 'health check' don't appear to mutate anything.

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?

The description is two words with no filler, so it cannot be called verbose, but this is under-specification rather than disciplined brevity, since critical context is absent. It earns a middle score for being tight while failing to earn its place with substance.

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 zero-parameter tool this is close to viable, but with no output schema and only 'health check' to go on, an agent cannot tell what kind of response to expect or how to interpret it. A single sentence stating what is verified and what a successful/unsuccessful result looks like would complete the picture.

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 zero parameters and the schema defines none, so the description has no parameter meanings it must explain. The baseline of 4 for a no-parameter tool applies; there is nothing missing in parameter documentation.

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 "Health check" is effectively a restatement of the tool name (get_healthz). It conveys the general domain but doesn't state what the check covers (e.g., service liveness, dependency status) or what a successful vs. failed result means, so it barely separates itself from a tautology.

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?

There is no guidance on when to call this tool versus any of the many sibling tools, no context about preconditions, and no exclusionary phrasing. An agent gets no hint of where a health check fits in a workflow (e.g., before running scenarios or querying data).

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