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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds concrete context beyond them: text-only edits replace explicit pages, page IDs stay stable, omitted address fields are preserved, and a fresh proof/quote/approval is required before editing. It does not explain what happens on a stale `version` (conflict/rejection), which is the main behavioral risk for a destructive same-revision edit.

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?

Front-loaded with the core edit semantics, then the destructive page-replacement rule, then address handling, then preconditions and retry. The telegraphic sentence fragments are dense but each carries a distinct rule, with 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?

Given 18 parameters, no output schema and destructive semantics, the description covers editing and addressing well but leaves a required parameter (`version`) unexplained in both schema and description, and gives no signal about the return value or failure modes of a conflicting revision. Adequate but with an important gap for a mutation tool of this complexity.

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 only 6% across 18 parameters, so the description must compensate and it does so for only part of the surface: pages/page_id preservation, text vs pages, sender/recipient objects vs sender_id/recipient_id, and idempotency_key. It says nothing about `version` (required optimistic-concurrency token), content_type, style, paper, envelope, decorations, or the handwriting configs.

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+resource ('Edit writing or supported options') on an existing draft in the same revision, which an agent can distinguish from create_draft or get_draft. The phrase 'supported options' is vague and only clarified later by the address/field examples, so the purpose statement is clear but not fully self-contained.

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?

Offers real usage rules: never guess missing details, edits require fresh proof/quote/approval, reuse the same idempotency key on retry. However, it never routes the agent to alternatives (create_draft for new letters, get_draft to read current state, quote_for_send before sending), so the guidance is implied rather than comparative.

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