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

Annotations already declare non-readOnly, non-destructive, non-idempotent, so the safety profile is covered. The description adds genuinely new behavioral context (untrusted-content handling, prompt-injection resistance, preserving uploaded PDFs as files), but a large block is a verbatim repeat of the content_policy_acknowledged parameter description, and nothing is said about what state a draft lands in, that it is unsent, or about idempotency_key behavior despite the idempotentHint=false annotation.

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 is front-loaded and the address guidance is tight, but roughly half the text is policy boilerplate duplicated verbatim from the schema's content_policy_acknowledged description, while the 14 undocumented non-address parameters get no space at all — the budget is misallocated rather than bloated.

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 16-parameter, non-readOnly creation tool with no output schema and near-zero schema description coverage, the description should explain the draft lifecycle and the main content/formatting parameters. It covers only addresses and policy, so an agent still cannot confidently construct pages, content_type, decorations, or idempotency_key from this definition.

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 6% across 16 parameters. The description explains only the sender/recipient address path (inline fields vs *_id reuse) and PDF handling; text vs pages, content_type, style, paper, envelope, decorations, title, handwriting/original_hand configs, and idempotency_key are entirely undocumented in prose, leaving the agent to reverse-engineer them from names and enums.

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 opening sentence gives a clear verb and resource plus an important scope qualifier: 'Create a letter without ordering.' That separates it from checkout/send_with_credits, but it never names create_template_draft or update_draft, the siblings closest to it, so the boundary with those is left to inference.

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 gives real operational guidance for addresses ('save customer-provided fields directly, or reuse confirmed address IDs', 'ask for missing details; never guess a ZIP'), which is useful when-to. But it never states when to use this over update_draft/create_template_draft, nor any prerequisite such as whether a draft must precede checkout, so usage is only partially routed.

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