tool_find_elements

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 useful behavior: 'Read-only', the minimum-one-filter constraint, that results are refs actionable via element_action, and the important caveat that a zero/minimized result is not proof of no match. It still omits behaviors such as what hwnd=0 means, how include_offscreen and max_results affect results, or ordering/truncation of output.

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-loads the purpose and constraint, then adds caveats; every clause is relevant. Slightly verbose in the middle ('the point of naming it is that you no longer need a pixel'), but no sentence is wasted.

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 7-param read tool with an output schema, the description covers purpose, precondition, alternative, and even one return field ('minimized'), which is a helpful bonus since output schemas don't explain semantics. The remaining gap is the undocumented non-filter parameters, which is a parameter-semantics issue more than a completeness one.

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% across 7 parameters, so the description must compensate — it explains role (lowercase skyshot roles, with examples) and effectively name_contains ('name substring'). However hwnd, title, max_results, automation_id, and include_offscreen receive no meaning beyond their names, so the compensation is only partial.

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+resource ('Find UI elements by role and/or name substring') and names the downstream consumer (element_action), which makes the tool's output role unambiguous. It also explicitly separates itself from tool_skyshot and explains the hit-testing use case, so an agent can distinguish it from siblings without opening the 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?

Gives an explicit when-to-use ('reach an element that cannot be hit-tested'), an explicit when-not ('an unfiltered call would be a tree dump, so use skyshot for that'), and names the follow-up tool (element_action). It even states a hard precondition — at least one filter is required.

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