Command-Line Message

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

Annotations only declare readOnlyHint=false and destructiveHint=false. The description goes further by stating 'Nothing in the drawing changes' (consistent with destructiveHint=false, since the write is to the prompt area, not the drawing) and by enumerating concrete failure modes: empty messages are refused and headless contexts require capability 'interactive_prompt'. That is real behavioral context beyond the structured fields.

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?

Purpose and constraints are front-loaded and the text is short. But 'Pack: settings · lean: no' is opaque internal jargon that an agent cannot act on, and it dilutes otherwise efficient prose.

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?

An output schema exists so return values need not be described, and the failure conditions are covered. Still, an agent gets no clear statement of the tool's role among siblings and the 'Pack/lean' shorthand is left unexplained, leaving the picture partially incomplete.

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?

With one parameter and 100% schema coverage, the baseline is 3. The description adds meaningful semantics beyond the schema's 'The message; one line is best': it specifies that an empty message is refused, which is a validation constraint the schema does not encode.

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 opening '`Utility.Prompt`: tell the operator something where they are looking' conveys that this surfaces a message to the user, and it is distinguishable from the many drawing-modifying siblings. However, the phrasing is oblique ('where they are looking') and the cryptic 'Pack: settings · lean: no' adds no clarity about what the tool actually does. Verb+resource is present but vague.

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 gives refusal conditions (empty message, headless without the interactive_prompt capability) which hint at when the tool will not work, but it never states when to reach for this tool versus alternatives or what it is for in a workflow. No positive usage guidance is offered.

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