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

With idempotentHint and destructiveHint already declared, the description still adds substantive behaviour: validation ('checks it as its website does (fit, names, the design's own words)'), page counting, and the fact that the call returns price plus a page-1 preview. The replace-on-recall statement reconciles cleanly with the idempotent hint rather than contradicting it.

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 key action is front-loaded and there is no filler, but the opening sentence is very long and packs enumerations into a single run of commas, which slightly hurts scannability. Nearly every clause still earns its place, notably the closing address warning.

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 12-parameter, nested-object, mutation tool this is complete: the prerequisite job handle, the catalog-sourced font/letter_type/stationery, the mailing enum, replacement semantics and the address exclusion are all covered, and the return behaviour is summarised even though an output schema exists.

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 92%, but the description adds meaning the schema does not: it explains the three mailing modes in plain terms (flat/tracked vs First-Class up to 5 pages vs Certified), and it reinforces the address prohibition that governs 'fields', 'greeting_name' and similar free-text inputs. It goes beyond restating schema prose.

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?

The description opens with a specific verb and resource ('Write a letter on a job') and enumerates the pieces that define the artifact: font, stationery, letter type, message, mailing method. The resource is unmistakably distinct from the postcard and text-document siblings, so an agent can route on the first clause alone.

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?

It states the prerequisite clearly ('on a job from hip_create_job') and gives a use-time constraint that matters ('Never include an address: the person enters the mailing address at checkout'). It also discloses re-call behaviour ('Calling it again replaces the letter'). It does not explicitly say when to prefer hip_set_postcard or hip_add_text_document instead, but the context is clear enough.

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