collect

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

No annotations exist, so the description carries the full burden and does disclose the key behavior: it iterates scrolling, deduplicates ('without repeats'), and terminates when nothing new appears or max_scrolls is hit. It omits side effects an agent should know about — the view is left scrolled somewhere new, and it presumably requires the target app in the foreground — but the core loop is transparently described.

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?

Three tight sentences, front-loaded with the mechanism, then the use case, then the parameter semantics. No filler or restatement of the tool name.

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 3-parameter tool with no annotations and no output schema, the description covers mechanism, termination, use cases and direction adequately. It stops short of describing what the collected output looks like (plain text blocks vs. screen-relative ordering) and how 'element' interacts with scrolling, which an agent would still have to discover by calling.

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 67%, and the weakest gap is direction, whose enum has no schema description; the description fills exactly that gap by mapping 'up'/'down' to older-vs-further semantics. element and max_scrolls are already documented in the schema, so the remaining description text adds the right marginal value.

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 and resource — reads a long list/conversation by scrolling and gathering visible text — and pins down the defining trait ('in one call', 'without repeats'). The 'in one call' framing implicitly separates it from read_screen (one snapshot) and scroll (movement only), so an agent can pick correctly without opening schemas.

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?

Gives concrete use cases ('summarize a chat, a feed or search results') and explains the direction choice ('up' for older chat messages, 'down' for further down a list). It lacks an explicit when-not clause or a named alternative (e.g. use read_screen for a single screen), which keeps it below a 5.

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