Run a quick print command

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is carried by structured data. The description reinforces the gate by stating confirmed=true is required, but it never discloses what is actually destroyed or consumed (paper, printer state, job submission) or whether the action is reversible. The framing as "parses" also mildly understates the destructive behavior the annotations declare, though it does not directly contradict them.

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?

A single tight sentence with no filler, and the precondition is placed after the capability rather than buried. Slightly back-loaded for a destructive tool, but there is no wasted text.

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 destructive, no-output-schema tool with zero parameter documentation, the description is thin. It says nothing about what a successful call produces, which printer/profile it targets by default, what "preview" and "force" actually change, or how failures surface — all things an agent needs before invoking an irreversible operation.

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 carry the load. It partially does: it identifies "command" as the argument text from /print and enumerates the kinds of tokens it may contain (flags, aliases, profiles, filters, preview, force), and it states the required value of "confirmed". It still omits the concrete syntax or examples of the command string, so compensation is incomplete.

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 verb is "parses" and the resource is "the argument text from /print," which is mechanically specific but leaves the user-visible effect ambiguous — it never states that a print job is actually submitted. It also fails to distinguish itself from close siblings like print_paths, estimate_print_job, or inspect_print_job, so an agent must guess which print entry point applies.

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?

It gives one real precondition — "Requires explicit slash-command intent and confirmed=true" — which tells the agent when the tool is legitimate. However, it names no alternatives and no when-not-to-use conditions, so the routing decision among the 17 sibling print tools is left entirely to inference.

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