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

Annotations declare readOnlyHint=false / destructiveHint=false; the description adds real behavioral value by clarifying that no state changes until confirm_change is called and that confirmed prompts are measured from the next audit. This resolves the ambiguity left by readOnlyHint=false for a 'prepare' tool. It does not cover re-invocation behavior, despite idempotentHint=false.

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?

Two tight sentences with no filler; the preview behavior and the no-change guarantee are front-loaded, and the audit-timing detail is a compact trailing clause.

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?

With no output schema, the description helpfully characterizes the preview result (which can be added, which are dropped and why, slots after) and the confirmation flow. The remaining gap is the undocumented parameters, which the schema does not describe either.

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 description coverage is 0%, so the description must carry the load. It only constrains the prompts array size (1–50) and mentions the prompt set target; project_id, prompt_set_id, and the nested text/cohort/intent/topic_id fields are left entirely to the schema. Partial compensation, not full.

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 (preview adding), resource (prompts into a prompt set), and scope (1–50). It is clearly distinguishable from the sibling prepare_archive_prompts and from read_prompt_portfolio.

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?

Explicitly frames this as a preview step and names the follow-up tool (confirm_change) plus the condition that gates it ("until the user agrees"). It does not spell out when *not* to use it or what to do if items are dropped, but the workflow context is unambiguous.

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