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

Annotations only declare readOnly=false/destructive=false; the description adds the crucial lifecycle detail that nothing mutates until confirm_change, and that confirmed prompts are measured from the next audit — behavior an agent could not infer from structured fields. It does not say whether a prepared change expires or can be re-run over an existing pending change.

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 dense sentences, front-loaded with the action and its output, followed by the safety/commit contract. No filler and nothing buried.

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 compensates by naming exactly what the preview returns (addable, dropped + reason, resulting slots), and the two-phase commit requirement is spelled out. For a staging mutation tool this covers everything needed to invoke it correctly.

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% and each parameter and nested prompt field is documented in the schema, so the baseline is 3. The description's '1–50 prompts' and 'to a prompt set' restate limits and scoping already encoded in minItems/maxItems and prompt_set_id's description, adding little new meaning.

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+resource ('preview adding 1–50 prompts to a prompt set') and enumerates the preview payload (which can be added, which are dropped and why, slot counts after). The explicit hand-off to confirm_change separates it from the sibling that actually commits the change.

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?

'Nothing changes until the user agrees and you call confirm_change' gives the gating condition and names the follow-up tool, so the agent knows this is step one of a two-phase flow. It stops short of contrasting with prepare_archive_prompts or stating when not to use it (e.g., already-prepared change pending).

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