Find Nodes

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

With no annotations, the description carries the full burden, and it does disclose two meaningful behaviors: filters are ANDed ('matching every given filter') and off-screen nodes are included. It says nothing about read-only safety, result ordering, duplicates, or behavior when no filters are supplied (all nine parameters are optional).

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?

A single sentence that front-loads the resource and matching rule, with the off-screen qualifier placed where it reads as a differentiator. No filler.

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?

An output schema exists, so return values need no explanation here. However, for a nine-parameter tool with zero schema descriptions and no annotations, the description omits the 'tree' and 'device' inputs and gives no explicit routing guidance against find_nodes_on_screen or get_ui_tree.

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 0%, so the description must compensate, and it does for most of the surface: it names text, desc, resource_id, class_name and the *_contains variants and explains exact-vs-substring semantics. It leaves two parameters, 'tree' and 'device', completely unexplained, which is a notable gap for an object-typed parameter.

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 (find) and resource (nodes) plus the matching semantics: exact match on text/desc/resource_id/class_name or substring via *_contains. The clause 'including off-screen ones' implicitly distinguishes it from the sibling find_nodes_on_screen, though it never names that sibling.

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?

Usage is only implied: an agent can infer this is the right tool when it wants nodes outside the current viewport, and that all filters are conjunctive. There is no explicit statement of when to prefer find_nodes over find_nodes_on_screen, get_ui_tree, or wait_for_nodes, nor any mention of required preconditions.

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