Restart Hermes gateway through configured command

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds meaningful context about the side-effect gating, policy tier requirement, and redacted artifact capture. The description complements rather than contradicts annotations, adding value about what conditions must hold and what output behavior to expect.

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?

Single dense sentence that packs in the key constraints. It's somewhat jargon-heavy but efficient. Could be split for readability but earns its space given the complexity of the gating conditions.

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?

A destructive, side-effect-producing tool with 7 parameters, 0% schema coverage, and a high-risk operation. The description conveys the critical gating context (owner tier, external-side-effect, command hash, nonce) and notes output redaction. However, it doesn't explain what the return output looks like (though an output schema exists, which reduces this burden) or detail failure modes like what happens when gates aren't met.

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 0%, so the description must compensate. The description names some parameters implicitly (confirmation nonce, command hash) but does not explain semantics for all 7 parameters like home, profile, toolkit_root, or timeout_seconds. The confirmation_nonce and expected_restart_command_sha256 are mentioned by name in the description, which helps, but the optional path parameters remain unexplained. Baseline is 3 given low coverage and partial compensation.

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 runs a preconfigured gateway restart command with multiple gating conditions. It distinguishes from siblings like hermes_gateway_status (status check) and hermes_deploy_repair_apply (repair) by specifying it's an actual restart action. Slightly dense phrasing but the verb+resource+scope is clear.

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 this is a privileged action by specifying 'owner policy tier' and lists several gating requirements (external-side-effect, allow_gateway_restart, command-hash, confirmation nonce). This implicitly tells the agent this tool requires owner permissions and specific preconditions, distinguishing when to use it. However, it doesn't explicitly name alternative tools or state when NOT to use it.

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