Get export preview

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the phrase 'Read-only' in the description earns no credit. What the description does add is genuinely useful: the result carries an `options` object enumerating every export_pdf choice with defaults, plus a `warnings` array and an error shape. It stops short of saying whether truncation at `limit` is silent or whether preview cost scales with album size, which are the remaining behavioral unknowns.

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 correctly: purpose, then constraint, then the options/ask-or-export decision, then args and return shape. Every sentence earns its place, though the Args/RETURNS block partially restates prose already given above it, and the parenthetical field list in the first sentence is dense.

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 three-parameter read tool in a two-step export workflow this is nearly complete: exclusivity rule, defaults, range, return shape and the options-driven conversation flow are all covered. An output schema exists so return values needn't be explained, and the only mild gap is not stating how `limit` truncation surfaces in `warnings`.

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%, so the description carries the full burden and does: album_id is an 'Album UUID', asset_ids are 'Explicit asset UUIDs (search results, a selection)', limit is 'Max assets (1-500, default 100)'. Crucially it also supplies the mutual-exclusivity rule that the schema (required: []) entirely fails to encode.

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 ('List what export_pdf would include') and enumerates the returned fields (id, type, filename, date, place, people, video duration). It also positions itself against the downstream sibling ('before ... writing captions'), so an agent can tell it apart from export_pdf and get_album_images without opening a schema.

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 decision rule for the hardest part of the workflow: when the user gave no specs, show `options` and ask; when they did, or said defaults are fine, export directly. It also states the invocation constraint 'Pass exactly one of album_id / asset_ids', leaving nothing to inference.

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