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 richly: it declares WRITE, human-gated approval via elicitation that overrides arguments, refusal for clients lacking elicitation (except dry_run), and a key contrast with the single call — existing codes are reported `skipped` rather than failing the batch. It also discloses the return shape (per-app outcome matrix plus created/skipped/failed 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?

Front-loaded with the core purpose and dense with useful detail; nearly every sentence adds a distinct operational fact. Slightly repetitive around the elicitation/human-gating point, which costs it a perfect score.

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?

Batch behavior, approval gating, skip semantics, and return counts are well covered for a complex tool, and no output schema exists to offload that. However, for a 10-parameter tool with 0% schema coverage, six parameters remain undefined, notably confirm_high_discount and max_uses/expires_at, leaving the agent under-informed on how to call 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 description coverage is 0% across 10 parameters, so the description must compensate but only meaningfully explains app_ids (pass explicit ids from list_apps) and dry_run (use first to preview). Code and discount are only implied, and listed, max_uses, expires_at, description, applies_to_tiers, and confirm_high_discount are left entirely undocumented in both description and schema.

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 precise verb+resource+scope: 'Create the SAME discount code across many apps in one call.' It explicitly frames itself as the bulk counterpart to create_coupon and adds the portfolio-promo use case, so an agent can distinguish it from the single-create sibling without opening the 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?

Gives concrete when-to-use guidance ('summer sale on every owned app'), a prerequisite (requires an elicitation-capable client; non-elicitation clients are refused), a recommended first step ('Use dry_run:true first'), and the alternative (create_coupon for single calls). It also warns there is deliberately no 'all apps' shortcut and to pass explicit app_ids from list_apps.

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