ACTION_READ_SCREEN

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

With no annotations, the description carries the full burden and discloses several non-obvious traits: it requires accessibility, screen_data is a boolean detection result rather than screen content, output is delivered as a variable-snapshot JSON, and string parameters accept ${var} interpolation. What is missing is timing behavior (does it wait/retry or take a single snapshot) and the format of the snapshot beyond the output_var newline-separated text.

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?

Very tight: purpose first, then the output-semantics caveat, then the interpolation note. Every clause disambiguates something an agent would otherwise get wrong, with 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?

For a five-parameter, annotation-less tool with no output schema, the description covers the environment prerequisite, the true return semantics, and how results land in variables. Only the timing/waiting behavior and the concrete shape of the variable snapshot remain unstated.

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 100%, so all five parameters are already documented, setting the baseline at 3. The description reinforces the schema's subtle points (keyword empty ⇒ false, output_var receives the text) and notes ${var} interpolation, but adds no new constraints or value formats beyond what the schema states.

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 two specific capabilities with a verb and resource: locate a keyword in the current UI, or capture all visible screen text (requires accessibility). It also pre-empts the most likely misreading by declaring that screen_data is a found/not-found boolean rather than the captured text. It never names the closest alternatives (ACTION_FIND_ELEMENT, ACTION_SCREENSHOT, ACTION_WAIT_FOR_ELEMENT), so a sibling-differentiation point is lost, but the tool's own scope is 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?

Implied routing is present: for text use output_var, and an empty keyword forces screen_data to false. The accessibility-service prerequisite is a useful usage gate. However there is no explicit statement of when to pick this over ACTION_FIND_ELEMENT or ACTION_WAIT_FOR_ELEMENT for element lookup, nor whether this tool polls or waits.

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