device_deck_probe_device

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

The description adds real detail beyond the annotations: it discloses the side effects (saves a local observation and an audit event), the hard boundaries (no arbitrary shell/UI execution, no pairing), and the partial-result semantics (missing fields remain unknown). These are exactly the facts an agent needs with openWorldHint=true. The only wrinkle is that "read-only probe" superficially reads against readOnlyHint=false, but the same sentence discloses the local write, so an agent is not misled.

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?

Four short sentences, front-loaded with the action and its restrictions, with no filler. The stacked qualifier list ('registered SSH, paired ADB, trusted iOS USB or existing WDA endpoint') is dense but each item carries information about accepted transport types.

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?

An output schema exists, so return values need no explanation, and the description covers scope, side effects, and boundaries well for a probe tool. The remaining gap is that two required parameters are semantically opaque in both the schema and the description, and there is no guidance on when to probe versus plan a connection.

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%: the schema gives only titles for device_id, endpoint_id, and response_format, and the description explains none of them. "One registered ... or existing WDA endpoint" loosely hints that endpoint_id must reference a pre-registered endpoint, but device_id versus endpoint_id and their relationship stay undefined, and "Missing fields remain unknown" is too vague to compensate.

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 specific action and resource: run a fixed read-only probe against a registered SSH, paired ADB, trusted iOS USB, or existing WDA endpoint. It also says what the tool produces, a local observation and an audit event. It does not name or differentiate itself from its siblings (list_devices, get_device, connection_plan), 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?

"Against one registered ... or existing WDA endpoint" implies the prerequisite that an endpoint must already exist, while "Never executes arbitrary shell/UI commands or performs pairing" cleanly states the negative case. However, no positive when-to-use condition is given, and none of the sibling tools are referenced, so routing between probe_device, get_device, and connection_plan is left to inference.

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