snapshot

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

No annotations exist, so the description carries the entire behavioral burden. It discloses the output shape and the `under-keyboard` sentinel meaning, which is genuinely useful, but says nothing about read-only safety, output size/truncation, ref lifetime or invalidation, or what happens when nothing matches. For a zero-annotation tool that is a substantial omission.

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 compact clauses, no filler, with the output format placed first. The telegraphed style ('refs', 'under-keyboard') is efficient but borders on terse to the point of requiring interpretation.

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 annotations, no output schema, and an undocumented parameter, this description must do heavy lifting. It covers the core return format, which is the most important part, but omits ref lifecycle, result-size behavior, and failure/empty cases that an agent calling a snapshot tool would need.

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% for the single `find` parameter, so the description must compensate and partially does: it says `find` lists matching lines and that `A|B` means either. However, it never clarifies the matching mode (substring, regex, case sensitivity) and the parameter name alone is ambiguous, leaving real gaps.

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 states a concrete result: the screen rendered as lines such as `@e4 button "Save"`, with refs that name elements for other tools. That tells an agent exactly what the tool produces. It stops short of distinguishing itself from the sibling `screenshot`, so the textual-vs-visual split is left to inference.

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: the note that refs 'name elements for other tools' hints this is the prerequisite call before tap/press, but there is no explicit when-to-use or when-to-prefer-`screenshot` statement. The `find` parameter's effect is described, which nudges toward the right invocation but not the right selection.

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