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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description goes further by explaining that re-calls replace rather than duplicate, that validation of message fit and card guidelines happens server-side, and that printing/mailing is full color, First-Class, untracked. It does not spell out failure behavior when validation rejects the message, which is the remaining gap.

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?

The core action is front-loaded in the first clause and the following sentences each carry operational information (validation, replacement, mailing, address prohibition). The opening enumeration partially restates schema fields, costing a little density, but there is no filler.

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 7-parameter write tool with a nested object, the description covers inputs, validation, replacement semantics, return contents (price and two preview images), and fulfillment constraints. With an output schema present it correctly avoids describing response structure in detail.

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 86%, so the schema carries most of the load, but the description adds real meaning: the font is a handwriting-style face drawn from hip_get_catalog, the front must be a catalog id, and sender_name is the signature line rather than an address. It does not mention front_fields, the nested object, which the schema only briefly labels.

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 ('Write a postcard on a job') and immediately enumerates the content the call defines: size, front, message, signature. It is clearly distinguishable from the sibling hip_set_letter and from hip_create_job, which it names as the source of the job handle.

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 prerequisites (job from hip_create_job, front from hip_get_catalog), states the re-invocation semantics ('Calling it again replaces the card'), and adds a hard exclusion: never put a mailing address on the card or in this call because the recipient supplies it at checkout. That is when-to-use, when-not-to, and where the alternative lives.

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