desktop_inspect

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

With no annotations, the description must carry the burden. It discloses key traits: the tree is bounded, element IDs are opaque and valid for 60 seconds. This is useful context. However, it does not mention that the operation is read-only, nor what happens on invalid window_id or when the tree exceeds the limit. It also doesn't state whether the returned IDs are intended for use with other desktop tools, which is a significant behavioral aspect.

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?

A single sentence that front-loads the core action and resource, followed by specific details on the returned data and ID characteristics. No filler or redundancy. It is concise while conveying multiple important points.

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 tool is part of a larger desktop automation suite, and the description mentions the expiring IDs but does not explicitly connect them to subsequent actions or tools. It also omits the effect of the limit parameter and how to obtain the window_id (e.g., via desktop_windows). While the core behavior is clear, these gaps make it incomplete for an agent to use effectively.

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%, and the description adds no meaning to the parameters. It doesn't explain that 'limit' controls the bound or how 'window_id' is obtained. The description's mention of 'bounded' is vague and does not connect to the limit parameter. The agent gets no help understanding the parameters beyond the schema's types and defaults.

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 clearly states the tool returns a bounded accessibility tree with specific content (roles, states, actions). The verb 'Return' and resource 'bounded accessibility tree' are specific and distinguish it from siblings like desktop_observe (likely for changes) or desktop_read_text. However, it does not explicitly name alternatives or contrast with them.

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 is given on when to use this tool versus alternatives. It does not mention prerequisites (e.g., how to get window_id) or situations where another tool would be more appropriate. The description only states what it does, not the context of use.

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