request_rh_pxe_boot

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

Annotations already declare non-read-only, non-destructive and open-world. The description goes further by disclosing the async ticketing workflow: a ticket is created for the datacenter on-call shift, status and correspondence live in the ticket, and the link is emailed. That is meaningfully beyond the annotation set, though it omits any expectation of latency or failure modes.

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?

Three tight clauses with the action stated first, followed by the trigger condition and the ticket mechanics. The parenthetical path is compact and the sentences all earn their place, though the last sentence is slightly dense.

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?

With no output schema, the description usefully pre-answers 'what happens next' by explaining that results arrive via ticket and email. Combined with full parameter coverage, an agent has what it needs to call this correctly; only latency/error expectations are unaddressed.

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%, so 'id' (Server ID) and 'confirm' (must be true) are already fully documented. The description adds only an indirect hint that the target is a server; it contributes no format or constraint detail beyond the schema, making the baseline 3 appropriate.

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 action ('boot the server via PXE') scoped as a Remote Hands ticket, and the internal marker (jira/request_PXEboot) pins the operation. An agent can distinguish this from request_rh_reboot, request_rh_power_on and request_rh_kvm without opening any schema.

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 condition ('needed when reinstalling OS on servers without a remote management module'), which is real routing context. It does not, however, name the sibling alternatives an agent might weigh (e.g. set_boot_device, create_reinstall_task), so it stops short of full when/when-not guidance.

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