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

Adds substantial context beyond the annotations: the 30-minute quote lifetime, that the PDF proof is an exact proof, that approval is bound to content and must be re-obtained after edits, and that full-profile guest quote IDs act as private bearer capabilities. These are non-obvious security and lifecycle behaviors an agent cannot infer from readOnlyHint/destructiveHint/idempotentHint.

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?

Four dense sentences, front-loaded with the action and scope, then the send_letter contract, then the re-quote rule and the security note. Every sentence carries information, though the send_letter sentence packs several constraints into one run-on clause.

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?

An output schema exists so return values need no explanation, and the mutation/approval lifecycle is well covered. For a 12-parameter tool with nested address objects and pricing side effects, however, the description leaves the pricing drivers (certified, doubleSided, color, couponCode interactions) and validation failure modes unexplained.

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 42%, so the description must compensate, but it only names categories ('artwork, sender, every recipient, options, expiry and total') without explaining any. Undocumented parameters such as mailClass (the one enum), certified, doubleSided, and electronicReturnReceipt carry cost and eligibility implications that go unaddressed—notably that 'certified' overlaps with the enum value 'certified'.

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?

Opens with a specific verb+resource: 'Create a saved 30-minute standard-letter or Express-postcard quote and exact PDF proof'. The scope (no charge, no send) separates it cleanly from send_letter and from the get_letter_quote/preview_letter siblings.

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?

Establishes the workflow: this must precede send_letter, which requires this quoteId, confirmed:true, matching approvedTotalCents and an idempotencyKey, and changed content forces a re-quote. Clear when-to-use context, but it never explicitly contrasts with preview_letter, get_letter_quote, or quote_product, so the sibling routing is only implied.

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