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

Goes well beyond the annotations: it enumerates the exact acceptance policy and the three rejection grounds, states a concrete 5 MB decoded size limit, and explains what gets created ('resubmitting the same file mints a new artworkRef rather than replacing the earlier one') — which independently corroborates idempotentHint=false. It also discloses the return payload (artworkRef, displayUrl, disc preview) and the human-approval boundary, so an agent understands side effects and follow-up obligations.

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?

Purpose and intake policy are front-loaded, then parameters, then return/approval behavior — a sensible order for a six-parameter write tool. It is dense but mostly earns its length; the approval sentence is slightly doubled ('Design approval stays human ... No tool ... records or implies an approval'), which is defensible as a guardrail but is the one redundancy.

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 six-parameter, nested-object write tool with no output schema, the description supplies what is otherwise missing: the return values, the non-idempotent creation behavior, the size/validity gate, and the fact that approval is out of band. Nothing an agent needs to call this correctly or interpret the result is absent.

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 100% and nested objects are fully described, so the schema already carries the parameter semantics. The description restates most of it (file contents, sha256 as hex digest of those bytes, shape, orderRef, logo, note) with only marginal added meaning, such as noting that omitting shape makes the preview show both shapes — which the schema also says. Baseline 3 is correct.

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 ('Send the finished artwork back') and immediately delimits scope: intake only, not production fitness, not approval. That scope framing distinguishes it cleanly from siblings like create_order and get_artwork_spec without the reader 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?

Gives explicit context for the two access paths ('No key and no email are needed on the cold path; a keyed submission binds to the key's organization') and clear exclusions ('Production fitness is judged later ... never here', 'No tool on this server records or implies an approval'). It also routes one parameter to a sibling ('the orderRef create_order returned'). It stops short of naming an outright alternative tool to use instead, so 4 rather than 5.

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