get_actuator_health

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

No annotations are provided, so the description must carry the burden of behavioral disclosure. It discloses that it probes the actuator /health endpoint and shows component detail, which is useful. However, it does not mention what happens on failure, whether it requires authentication, likely response format, or if it could be slow due to multiple indicator calls. It also does not note that 'pod' and 'service' are alternatives, which is implied by the schema. The disclosure is minimal but not misleading, so a 3 is fair.

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 a single sentence that is concise and directly states the core function. The '[probe]' prefix is unusual but adds a signal for the agent that this is a probing action. No fluff or unnecessary detail. It is appropriately sized and front-loaded with the action and endpoint.

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?

Given the tool's moderate complexity (3 parameters, no output schema), the description is somewhat incomplete. It does not explain how to choose between pod and service, nor does it mention that namespace is required even though it is marked as not required in the schema (but described as required in parentheses). The description covers the 'what' but not the 'how' or 'when' edges. For an agent to choose this among 40+ siblings, it needs a bit more context on when this is the go-to tool versus get_jvm_health or get_connection_pool_status. So a 3 is appropriate.

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%, with detailed descriptions for each parameter (pod, service, namespace). The description adds the context of which components will be checked, which could influence which parameters to use (e.g., service might be more suitable for deployments). However, it does not explain the relationship or priority between pod and service (e.g., which takes precedence), so it adds modest value beyond the schema's already thorough 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 clearly states the tool calls the actuator /health endpoint and lists the specific components (db, diskSpace, redis, custom indicators). It distinguishes it from sibling health tools like get_jvm_health which focuses on JVM, and health_report which is a broader diagnostic. However, it does not explicitly differentiate from similar health checks like get_connection_pool_status, but the endpoint-specific phrasing is clear enough.

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?

The description implies usage: when you need health details from the actuator endpoint, particularly for DB, disk, Redis, and custom indicators. However, it does not provide explicit guidance on when to prefer this over other health-related tools (e.g., get_jvm_health, health_report, get_connection_pool_status). The naming and description suggest it, but it is not explicitly stated, and there is no mention of prerequisites such as needing a metrics endpoint or using list_namespaces first.

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