control_print

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

Annotations already flag destructiveHint=true, and the description usefully adds what the tool will NOT do (never auto-resumes, clears faults, retries, or elicits approval) plus the binding/journaling effect of job_id on pause/cancel. However, the sentence 'confirmed:false never establishes execution' refers to a field that does not exist in the schema, which muddies rather than clarifies behavior for a destructive operation.

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?

Dense and front-loaded: the action set leads, followed by preconditions, then explicit non-behaviors. Almost every clause earns its place except the unexplained 'confirmed:false' clause, which adds ambiguity rather than 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 3-parameter destructive tool with no output schema, the description covers preconditions, non-actions, and the fact that state is verified after the call. Gaps remain around what cancel does to the job afterward and what 'verify its state' returns, but nothing essential to invoking it correctly is missing.

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 only 33% (only route is documented), so the description must carry weight; it does explain the resume-specific meaning of job_id and its binding/journaling role for pause/cancel. But action values are only partly elaborated, job_id's format is never described, and 'confirmed' is referenced without being a parameter at all.

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 opens with a specific verb set and resource: pause, cancel or resume a print, plus a verification step. 'Freshly identified print' and 'then verify its state' implicitly separate it from prepare_job and print_job, but no sibling is named, so the boundary must be inferred.

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 concrete preconditions for the riskiest action ('Resume requires managed job_id, a paused target and no printer faults or HMS warnings') and clarifies job_id is optional for pause/cancel. It does not name alternative tools, e.g. that printer_status or diagnose should be consulted for faults, so the routing guidance stops short of explicit alternatives.

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