desktop_inspect

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

With no annotations, the description carries the full burden: it declares the tool read-only and discloses the fallback path to D1 vision when accessibility data is unavailable. It does not discuss permissions or rate limits, but the read-only and fallback behavior are the key traits for this inspection tool.

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 sentences, front-loaded with the core purpose and followed by usage guidance. The return list is dense but earns its place, and there is 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?

The output schema already describes the return shape, so the description need not repeat it. Given no parameters and a read-only inspection role, the description covers purpose, usage, and fallback behavior sufficiently, though it could mention when inspection is unnecessary.

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 tool has zero parameters, so there is no parameter semantics to explain; the description correctly does not invent any. Baseline 4 applies for a parameterless tool, and nothing in the description contradicts the empty schema.

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 verb (inspect), a specific resource (foreground app), and enumerates what it reads: platform requirements, accessible controls, and detected drawing canvas. It is clear enough to distinguish from the mouse/click/draw siblings, though it does not explicitly differentiate from visual_assert or wait_until_ready.

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?

It gives actionable downstream guidance: use exact labels from this tool in smart_click/smart_type for the fast path, and fall back to D1 vision when accessibility is unavailable. It does not state explicit exclusions or when not to call desktop_inspect, but it provides clear usage context.

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