ssh_health_check

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states the tool is read-only ('only reads metrics and changes nothing') and describes the output structure (parsed JSON, critical_issues list). It also mentions the default value of 'detailed' and what it includes. It does not cover error handling, authentication prerequisites, or behavior on SSH failure, but for a health check these are secondary. The disclosure is strong but not exhaustive.

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 four concise sentences, each adding a distinct piece of value: purpose, safety guarantee, parameter behavior, and output highlights. It is front-loaded with the primary purpose and avoids redundancy. No sentence is wasted; the structure is efficient and informative.

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 (2 params, no output schema, but no nested objects) and the fact that there are no annotations, the description is remarkably complete. It specifies the return format (parsed JSON), the key fields (status, CPU, memory, disk, uptime, critical_issues), and parameter behavior. The only missing aspects (error handling, auth details) are likely standard across the ssh_* family and adequately implied by the context. Nothing essential for correct invocation is absent.

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 coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema: for 'detailed', it clarifies the default (false) and the specific additional metrics (load average and network). For 'server', it implies a predefined named server rather than arbitrary host string. These additions exceed the schema's minimal descriptions, thus warranting a 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?

The description states a specific verb ('Runs'), a resource ('the named server'), and a defined outcome ('returns parsed JSON with overall status, CPU, memory, disk usage, and uptime'). It clearly distinguishes this from siblings like ssh_execute (arbitrary commands) and ssh_monitor (likely continuous monitoring) by emphasizing 'read-only health check' and 'diagnostic shell commands'.

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 for one-off health diagnostics and explicitly notes it 'only reads metrics' and 'changes nothing', which suggests safe, non-disruptive use. However, it does not explicitly name alternative tools or state when not to use it (e.g., 'for ongoing monitoring, use ssh_monitor' or 'for arbitrary commands, use ssh_execute'). The context is clear but lacks explicit exclusions.

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