resize_hidden_window

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false). The description goes beyond that by disclosing the per-call ownership/ancestry verification requirement, the negative scope (no activation/showing/termination), and that rectangles are physical pixels — meaningful context annotations cannot express.

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 lines, front-loaded with the core action, then scope limits, then units. No filler, though the precondition and exclusion lines are terse enough that they read as fragments rather than fully developed guidance.

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 returned rectangles need not be explained. But with eight undocumented required nested parameters at 0% coverage, the definition stops short of explaining what each identity field must contain or what failure looks like when identity checks mismatched, leaving a real gap for a mutation tool with no schema descriptions.

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 coverage is 0% and the eight required fields (handle, pid, creation_filetime, executable_path, desktop_name, expected_outer, width, height) have no descriptions at all. The description adds partial meaning — 'outer geometry' maps to expected_outer and physical-pixel units apply to width/height and returns — but it leaves the identity fields (pid, creation_filetime, executable_path, handle) largely for the agent to infer from the precondition sentence.

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 (resize), a narrowly scoped resource (an exact named hidden desktop HWND), and the identity/geometry basis for the operation. The word 'hidden' plus 'exact named' distinguishes it cleanly from the sibling resize_window and move_window tools without opening any schema.

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 a clear precondition ('Caller must freshly verify launch ancestry and HWND ownership before each call') and a useful exclusion list (no title selection, desktop discovery, activation, showing, termination), which scopes the tool well. However, it never names an alternative tool for visible windows or for discovery, so the agent must infer the routing rather than being told.

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