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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so "Read-only" in the description earns no credit — it merely repeats structured data. The added value is modest: the pricing figures (draft 5, final 20 per image; 5 for a layout without an image; 20 for AI copy once per order) tell the agent this catalog is the cheap first call rather than a chargeable action, but no statement covers freshness, caching, or how the reference data relates to actual order state.

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 core purpose is front-loaded, but the body is a single ~90-word sentence that piles up category lists, per-image credit prices, and six niche-preset examples (webinar, cohort enrolment, early-bird tickets, client case, expert post, seminar invitation, B2B offer). The parenthetical price and preset enumerations could be trimmed without losing routing value, and the run-on construction hurts scannability.

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 carries the burden of conveying what comes back, and it does so thoroughly by listing the returned categories (formats, qualities, prices in credits and euro, presets with required facts, and the specific limits on variants, formats, images, orders in progress and orders per hour). The remaining gap is structural: it never says how that catalog is organized or how large it is, which matters for an agent budgeting context.

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?

The schema has zero properties, so the baseline applies: there are no parameters whose meaning could be lost. The description correctly implies a no-argument, whole-catalog fetch rather than a filtered query, which matches the empty object 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?

The description names a concrete resource — an ordering catalog for «Центр креативів» — and enumerates exactly what it exposes: formats (key, size, aspect, channel), channels, goals, tasks, layouts, qualities, prices, niche presets, and order limits. That enumeration plus "Start here" makes it immediately distinguishable from the operational siblings (creative_order, creative_estimate, creative_list).

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?

"Start here" is explicit call-ordering guidance: consult this reference before ordering or estimating. What is missing is a when-not clause — nothing says, for example, that this is not the tool for pricing a specific configured order (that would be creative_estimate) — so the routing is clear but not fully delimited.

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