file_exists

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

With no annotations, the description carries the full behavioral burden but only states the return shape, which the output schema already covers. It says nothing about whether this is a safe read-only probe, how as_root affects execution, or which device is targeted when serial is omitted.

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?

Two tight sentences, purpose front-loaded, zero filler. Nothing to trim.

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?

The output schema covers return values, so that omission is fine, but a 3-parameter tool with 0% schema coverage and no annotations leaves device targeting and root behavior undocumented. For a multi-device ADB surface this is a real gap.

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% for all three parameters, so the description must compensate and does not. 'path on the device' loosely hints at remote, but serial (device selection) and as_root (privilege escalation) are never explained anywhere.

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 ('Check whether a path exists') and even names the return shape. It distinguishes itself from mutation siblings like write_file/delete_file, but does not explicitly differentiate from stat_file, which likely answers a similar question.

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?

No guidance on when to prefer this over stat_file or list_files, and no mention of prerequisites such as needing an attached device or root access. The agent is left to infer context entirely.

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