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

Annotations already declare readOnly, idempotent and non-destructive, so the safety surface is covered. The description adds genuinely useful non-schema behavior: the result is shown in chat, it links out to the editor for fine-tuning or printing in drawn styles, and nothing is saved or purchased. It stops short of describing pagination/return payload nuances, but for a read-only generator this is strong.

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 purpose, then usage, then input, then behavior — good ordering. The gift-occasion enumeration (anniversary, Valentine's, wedding, engagement, housewarming, marathon, birthplace) is long but serves as trigger vocabulary for this tool, so it mostly earns its place; it borders on bloated.

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 45-parameter, nested-object tool with no output schema, the description covers the essential decision path: when to use it, what minimal input is required, and what happens to the design. It omits explicit direction to the sibling tools (list_themes for `theme`, search_location for resolving `place`), which leaves a small gap for an agent needing to populate the enum-constrained fields.

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?

With 45 parameters and 93% schema coverage the schema carries most parameter meaning, so the baseline is 3. The description adds real value on top: it tells the agent the minimum viable input ("Give a `place` or `lat`/`lon`; the rest is optional") and clarifies the multi-place limit ("up to three places") that spans `place` plus `more_places`, which a reader would otherwise have to infer.

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 opening sentence states a specific verb and resource ("Designs a map poster and shows it in the chat") and the description later names siblings like the MapPoster editor link and list_themes-adjacent concepts. An agent can distinguish it from search_location and list_themes without opening a 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?

Explicit when-to-use (map poster, map print, wall art, wallpaper, gift scenarios tied to a place) and explicit when-not (gift advice, directions, travel plans, star/night-sky maps, photo posters, 3D/wooden/scratch-off maps, hiking trails/GPX). Rival conditions are spelled out rather than left to inference.

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