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

Annotations already declare non-readOnly, idempotent and non-destructive, but the description adds substantial context beyond them: the human-gated elicitation requirement, that the form overrides the passed arguments, that non-elicitation clients are refused (except dry_run), and that actual create is guarded per-app. It even discloses the batch semantics (already-present codes are `skipped` rather than failing) and the return shape (per-app outcome matrix plus counts).

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?

The most decision-critical facts (what it does, human-gating, the batch skip behavior) are front-loaded, and every sentence carries information. It is somewhat dense and a couple of the parenthetical asides could be trimmed, but there is little wasted text.

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?

For a mutation bulk tool with no output schema, the description still explains the return value (per-app outcome matrix plus created/skipped/failed counts) and the approval flow. The remaining gap is the undocumented optional parameters, which is captured under parameter semantics; overall it is complete enough for an agent to call it safely.

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% across 10 parameters, so the description carries the burden. It clarifies app_ids provenance (from list_apps), the semantics of dry_run, that code and discount_percent define the coupon, and that 'coupon terms' are entered once via the form overriding the args. But it leaves listed, max_uses, expires_at, description, applies_to_tiers and confirm_high_discount unexplained, so it only partially compensates for the coverage gap.

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 description states a specific verb and resource ('Create the SAME discount code across many apps in one call') and immediately distinguishes it from the sibling create_coupon ('Runs each app through the same fully-guarded create as create_coupon'). An agent can tell exactly what this tool does and how it differs from single-create without opening any schema.

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?

It gives explicit when-to-use ('portfolio-promo shortcut'), a recommended precondition ('Use dry_run:true first to see which apps would create vs skip'), and a hard constraint ('Pass explicit app_ids (from list_apps)'; 'deliberately no all apps shortcut'). It also names the behavioral contrast with the single-call alternative. This is about as complete as usage guidance gets.

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