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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavior: the tool itself does not generate anything, it returns settings derived from app defaults and the world's elevation-data limits plus a deep link the user must confirm with Generate. It also flags the constraint that a coordinate link cannot carry settings, which the annotations cannot convey.

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?

Three sentences, front-loaded with the core purpose and output, followed by usage condition and input/override rules. Every sentence carries information, but the opening sentence is long and nested, packing purpose, data sources and return value into one clause chain.

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 8 parameters, no output schema, and rich annotations, the gaps an agent would otherwise face are covered: what the tool returns (settings plus a clickable link), what happens next (user presses Generate), which inputs are mutually exclusive, and which settings are agent-chosen versus defaulted.

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 100%, so the baseline is 3. The description still adds meaning the schema does not: that shape, size and relief are optional overrides with app defaults otherwise applied, that place and lat/long are mutually exclusive input routes, and that the latitude/longitude path loses the settings payload. That is above-baseline value, though not per-parameter detail.

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 specific verb and resource: 'Suggest OrbitStudio settings for a 3D-printed puzzle or ornament of a place,' and adds that it returns a deep link with settings pre-filled. Nothing in the sibling set (get_preview, list_worlds, search_places, star_map_link) does this, and the description makes the distinction obvious 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?

'Use it when the user wants to make or print a model of a specific place' gives a clear triggering context, and it routes input selection by naming search_places as the source for a place versus raw lat/long. It stops short of stating when NOT to use the tool (e.g. when the user only wants to view or preview a map), so it is a 4 rather than a full when/when-not treatment.

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