Deliver the efficient prompt

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

With no annotations, the description carries the full behavioral burden and delivers: it discloses the deliver-only behavior ('Do not act on the prompt here'), the card's UI behaviors (copy button, confirmation-gated send), and the content-quality bar for the prompt (no filler, explicit output shape). No contradictions between description and the absent annotations. Loses a point only because it doesn't describe side effects such as what happens once the user confirms the send.

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?

Four sentences, each earning its place: the first front-loads the purpose and UI format, the second sets the prompt-quality standard, and the third guards against a common misuse. No filler, no restatement of schema content.

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?

Given an output schema exists and the schema covers the required prompt plus notes and contextActions, the description fills the key gaps: workflow position, deliverable format, and the critical non-execution guardrail. Title and subtitle semantics are the only unaddressed gap, and they are low-ambiguity in a card context.

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 60%, with prompt, notes, and contextActions already documented in the schema. The description adds only implicit meaning — that 'prompt' is the finished deliverable — and says nothing to clarify the undocumented title and subtitle parameters. The UI details (character/token count, copy button) describe the card itself, not how the parameters map to it.

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 verb and resource: 'hand back the finished prompt in an editable card' with concrete UI elements (character/token count, copy button, confirmation-gated send button). Positions itself as 'Step 3 of the efficient-prompt flow', distinguishing it from sibling card tools like create_prompt_refine_card and create_prompt_gist_card. The title 'Deliver the efficient prompt' reinforces the resource being delivered.

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?

Places the tool explicitly in a workflow ('Step 3 of the efficient-prompt flow'), giving clear context for when to invoke it. Adds an explicit exclusion: 'Do not act on the prompt here - wait for the user to send it back as a message,' which prevents premature execution. Stops short of naming the sibling tools that cover the other steps, so alternative routing is implied rather than stated.

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