find

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

With no annotations, the description carries the burden and does disclose the core loop and the two-state return (FOUND with location / NOT FOUND). It omits the operational consequences: that up to 30 scrolls may be slow, and what state the screen is left in when the text is never found — meaningful gaps for a screen-driving tool.

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?

Two sentences, front-loaded with the core behavior and followed by the return contract and next step. The parenthetical examples of what counts as text are compact and earn their place; only minor slack.

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?

No output schema exists, so the description must define returns — it does state FOUND/NOT FOUND and that FOUND includes a location, which is the key contract. But "where it is" is left vague (coordinates? element id?) and there is no note on timing or post-failure screen state, leaving the picture partial for a 4-parameter device-automation tool.

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 documents text, element, direction and max_scrolls. The description adds only the matching intent ("some text is on the screen") and nothing about direction, element targeting, or the scroll budget, so baseline 3 applies.

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 gives a specific verb and mechanism — scroll repeatedly until the target text appears, then stop — which is clearly distinct from a plain scroll or read_screen. It does not explicitly name the sibling it replaces (scroll), but the search-and-stop semantics are unambiguous.

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?

"call read_screen to act on it" gives a clear next step after a successful find, which is useful routing guidance. However, it never says when NOT to use this (e.g., if the text is already visible, or when wait_for is the better choice for dynamically loading content), so usage is only implied.

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