Read-only server commands to run

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the description's 'It runs nothing and connects to nothing' reinforces rather than carries the safety profile. It does add real behavioral context beyond the annotations: output is names-of-env-files only (never values), unknown values remain as <placeholders>, and the human must run the commands as root and paste results back — a non-obvious two-party interaction. It stops short of saying what the placeholders block or what happens if the user pastes partial output.

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 purpose and the alternative-tool routing are front-loaded, and no sentence is filler. However, the middle is one long comma-chained enumeration of return content that duplicates what the output schema already declares, which lengthens the definition without adding decision-relevant 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 six-parameter read-only tool with full schema descriptions, complete annotations and an output schema, this is close to sufficient: it covers purpose, safety, placeholder behavior, and the hand-off to server_discover. The remaining gap is procedural — it does not say what the agent should do with the pasted-back output or that phase 2 feeds server_discover.

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 schema already documents all six parameters, and the baseline is 3. The description earns above that by explaining the semantics of the five optional parameters as a group: known values are filled in and unknown ones stay as <placeholders>, which tells the agent it can call with only the required domain and still get useful output.

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 and resource: it returns a block of read-only commands for the user to run as root on the Plesk server and paste back, tagged as phase 2. The enumeration of what the block covers (Plesk/OS, PM2, systemd, ports, nginx, docroot, git status, env file names, databases, crontabs, exposure checks) makes it unmistakable against siblings like server_discover or deploy_logs.

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?

Gives an explicit triggering condition ('when you can't reach the server yourself') and an explicit ordering rule relative to a named sibling ('or before server_discover'). The agent knows both when to choose this tool and where it sits in the workflow without opening any other definition.

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