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

Far exceeds the annotations: it discloses the elicitation/human-in-the-loop gate, that argument values are only a proposal overridden by the human form, the side effects (coupons row + best-effort Stripe mint with checkout backfill), the normalization/unique constraint on code, the free-only-app limitation, and the three non-negotiable house rules (6-month max expiry, 90%+ forced invite_only, 90%+ tier pinning). None of this is recoverable from readOnlyHint/openWorldHint/idempotentHint.

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?

Roughly 200 words but densely packed with non-redundant operational facts, and the most decision-critical items (WRITE, human-gated, dry_run) are front-loaded before the house rules. A few clauses, such as the parenthetical Stripe fallback detail, could be trimmed without losing selection value.

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 10-parameter mutation tool with no output schema, it covers side effects, failure modes, defaults, next-step verification and business constraints well enough to call it correctly. The remaining gap is per-parameter semantics for max_uses/description/listed and confirmation of what confirm_high_discount does versus the automatic house rules.

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 0%, so the description carries the burden and does substantial work: dry_run semantics, expires_at default (omitting means 6 months, not never), applies_to_tiers default (all paid tiers), code uppercasing/uniqueness, and the discount_percent 90%+ consequences. However max_uses, description, listed, app_id and confirm_high_discount are never explained, leaving roughly half the parameters undocumented anywhere.

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?

Opens with a concrete verb+resource ("Create a percentage discount coupon for an app") and immediately flags it as a WRITE, human-gated operation, so the agent knows exactly what kind of effect to expect. It never names the obvious sibling bulk_create_coupon, so differentiation from that tool is left implicit (singular vs. bulk) rather than stated.

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 prescribes the pre-flight ("Set dry_run:true first to preview the exact row without writing"), the post-flight ("Use list_coupons afterwards to confirm"), and where to find tier slugs ("list_plans"). It also states a hard gating condition — clients without elicitation are refused while dry_run still works anywhere — which tells the agent exactly when the call will and will not succeed.

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