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

Annotations already declare readOnlyHint=false and idempotentHint=false, but the description supplies the practical consequence: each call persists a new copy, so retries accumulate duplicates rather than overwriting. It also discloses that validation against printability happens before storage and that no order is created, which the annotations alone do not convey. It does not describe failure modes (what happens when no logo is found on the website), which keeps it off 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 short sentences, front-loaded with what the tool does and its sources, then the input constraint, then the return value and side-effect. Every clause carries a distinct fact with no restatement of the title or name.

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 three-parameter tool with a nested file object and no output schema, the description covers the accepted inputs, the one-of constraint, the validation step, the returned logo_ref and its consumer, and the fact that repeated calls create copies without ordering. Nothing an agent needs in order to call it 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 coverage is already 100%, so the baseline would be 3, but the description adds a constraint the schema does not express: exactly one of the three sources must be given, even though the schema's required list is empty and contains no oneOf. That mutual-exclusivity rule is real meaning beyond the structured field definitions.

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 (fetches a logo) plus the three accepted sources, the validation step (checks it can print on the mug) and the persistence step (stores it for a draft order). Naming create_draft_order as the consumer of logo_ref separates it cleanly from the sibling that actually places the order.

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?

"Give exactly one of logo_file, image_url or website" is a concrete selection rule for the three inputs, and "places no order" tells the agent this is a preparatory step before create_draft_order. It stops short of an explicit when-to-use statement or a named alternative for cases where the logo already exists, so it is clear context without stated exclusions.

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