phone_find

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

With no annotations, the description carries the full burden. It does disclose the experimental status and external dependencies, which is genuinely useful behavioral context an agent can act on. It omits what happens when the text is not found, whether it only reads or also interacts, and what the result looks like.

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 short sentences with the EXPERIMENTAL caveat front-loaded, which is the right ordering for a warning. Nothing is wasted, though the brevity is partly under-specification rather than economy.

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 and no output schema, the description should explain what is returned (coordinates, bounding boxes, match count?) and what failure looks like. For a tool whose whole value is the located result, that gap is material.

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?

The single 'text' parameter has 0% schema description coverage, so the description must compensate and does not: no indication of exact vs. substring vs. regex matching, case sensitivity, or whether the string targets visible UI labels. Only the verb 'locate' hints at intent.

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 and resource: 'Locate text on the iPhone screen.' An agent can distinguish this from the mac_* and browser_* families by platform. It does not differentiate from the sibling phone_ocr, which plausibly overlaps (find text vs. read text), so it stops short of a 5.

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 real prerequisites (iPhone Mirroring, python3 with pyobjc) and flags EXPERIMENTAL, which tells the agent this may fail and needs setup. But it never says when to choose this over phone_ocr or phone_tap, nor what conditions make it unusable.

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