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

Annotations already declare readOnlyHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: newest-first ordering, prompt truncation with a trailing …, and the "Same prompt as above." deduplication quirk, meaning a caller must use generation_ids to get full prompts. That last point is the kind of trap-avoidance context annotations cannot express.

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 in the first clause, with the sibling contrast and parameter guidance following. The single long sentence is dense with parentheticals, which slightly taxes readability, but no clause is padding.

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 carries the return-shape burden and mostly does so: per-generation status, file urls, prompt (with truncation rules), and the roll's @elements. It does not state that a next_cursor is returned, though the cursor parameter's schema text implies it.

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 coverage is 75%, so the schema already carries descriptions for query, cursor and generation_ids. The description still adds value by re-framing query as "find 'the one where…'" and by stating that generation_ids yields full prompts — a result-side consequence the schema omits.

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?

"Read one roll of images, video and sound, newest first" gives a specific verb, a bounded resource (one roll), the media types returned, and the ordering. It also explicitly partitions scope against a sibling: the roll's own @elements here versus the space's in list_elements.

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?

The description names when to use each optional parameter (query for "the one where…" prompt searches, cursor to read on, generation_ids for specific generations) and states where roll_id comes from (list_space or a storyboard). It stops short of stating when not to use this tool, e.g. browsing a whole space without a known roll id.

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