Prompt Gate (user-confirmed)

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

With no annotations, the description carries the full burden and does so well: it discloses the elicitation fallback, the `pending_user_selection` result shape, that cancellation is a distinct outcome that never yields an approved prompt, and that the server auto-detects and preserves language. These are exactly the behavioral traits an agent needs before calling.

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?

Front-loaded with the core purpose and outcome, then organized under a clear CALLING GUIDE heading. It is longer than typical but nearly every line carries routing or sequencing information; only mild repetition between the prose and the parameter notes.

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?

There is no output schema, so the description must describe returns — and it does: the approved prompt, the distinct `pending_user_selection` payload, and the cancellation outcome. For a six-parameter, two-phase tool with no annotations, nothing essential 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 100%, so the baseline is 3, but the description adds calling-order semantics not obvious from the schema: which parameters belong to the first call versus the second, and the practical guidance that `light` suits one-shot answers while `detailed` is for full specs. This meaningfully extends the field descriptions.

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 two-step action (generate a rewritten prompt, then obtain user selection) and a precise scope: 'Returns only the approved prompt.' It distinguishes itself from a plain rewrite by making user confirmation the core behavior, though it never names the sibling `rewrite_prompt` to contrast against.

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 CALLING GUIDE is unusually explicit about the first vs. second call, when to pass `selection`, when to omit it, and 'Never auto-select.' It also gives clear when-to-use rules for `rewrite_level` and `language`. The one gap is that it never routes the agent between this tool and the sibling `rewrite_prompt`.

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