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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world, but the description adds real value: success does not guarantee the panel rendered, retry must not repeat writes, and content trust rules for PDFs, letter text and draft fields. The only gap is that it never explains what the panel actually shows or whether anything is persisted, which matters given readOnlyHint=false.

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 when-to-use constraint is front-loaded and each sentence carries operational content (retry policy, trust rules). It is a dense paragraph of long compound sentences, and the untrusted-content sentence is broad boilerplate that could be tightened, but there is little outright waste.

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?

With no output schema the description need not describe return values, and it covers failure recovery and data-trust well. However, for a 2-required-parameter tool with zero schema coverage, it leaves draft_id/version semantics entirely unexplained, so an agent cannot confidently construct the call from this definition alone.

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 0% and the description never mentions the two required parameters. 'This existing result' and 'the same saved draft' loosely imply draft_id addressing, but nothing explains what version means, how it is obtained, or what happens on a stale version.

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 frames the tool as an 'optional inline proof' that is 'never the default writing/review path', which hints at rendering a letter proof but never states plainly that it displays a letter preview from a saved draft. The verb is ambiguous ('show' vs 'render a proof panel'), and it does not name the sibling tools (preview, get_proof, get_draft) it replaces. An agent can infer the display intent but has to guess at the concrete action.

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 an explicit when ('only when the user explicitly requests it') and an explicit when-not ('never the default writing/review path'), which is stronger than most definitions. It also prescribes a fallback path on render failure (panel 'Try again' once, else the review_url) but does not name any sibling tool as the alternative, so routing is by condition rather than by tool name.

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