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

Annotations only flag non-readonly, non-idempotent, non-destructive and closed-world; the description adds real meaning on top — that each successful call creates a new (non-idempotent) design, that storage is unlisted, and that no order is placed. It omits auth/permission requirements and rate limits, which keeps it short of a 5.

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 action and its outputs, then the input rule, then the negative guarantees. Every sentence carries distinct information with no padding.

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 usefully characterizes return values (browser link and assembled-deck picture) and covers the either/or input mode for a tool with nested composition objects. Minor gap: the locale enum and its default have no explanation anywhere, but nothing an agent needs to call the tool correctly is missing.

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 already 80%, so the baseline is 3. The description adds a constraint the schema cannot express — exactly one of image_base64 or composition — which is genuine value beyond structured fields, though it adds nothing for the undocumented locale parameter.

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 ('Saves finished artwork on a skateboard deck') and enumerates tangible outputs (browser link for 3D preview/editing/ordering, plus an assembled-deck picture). It also distinguishes itself from the create-vs-read sibling get_deck_spec by describing a creation role, so an agent can tell them apart without opening either 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 a concrete input constraint ('Takes exactly one of image_base64 or composition') and clear exclusions ('generates no AI artwork and places no order'). It does not explicitly name get_deck_spec or say when to prefer it over this tool, so routing guidance is strong but not fully closed.

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