kde_window_wait

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: a hard 60-second ceiling, a uniqueness requirement on the match, and the two optional wait conditions. It does not say what happens on timeout (exception, null, empty result) or whether polling backs off, which is the key behavioral unknown for a blocking 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?

A single dense sentence with the action and the two termination modes front-loaded; nothing is padding. The 'up to 60 seconds' restates the schema maximum, a minor redundancy, and the sentence would parse more easily split in two.

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?

There is no output schema, so the agent must be told what a successful wait returns (a window identifier? a match object?) and what a timeout yields, and the description covers neither. For a blocking polling tool with a required session selector and a uniqueness constraint, this leaves the caller guessing at the critical edge case.

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 low at 17%, so the description carries real weight and does explain the semantics of two otherwise opaque booleans ('until KWin reports fullscreen', 'geometry fills a logical display') and implies title/app_id matching. However, it never explains the required 'session' selector's meaning or the timeout default of 10s, leaving half the parameters undocumented in both schema and description.

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 and resource: wait for a window matching criteria, with optional fullscreen/geometry-based termination. The scope is clear enough to distinguish it from kde_window_find or kde_window_list (which presumably return immediately). It stops short of naming a sibling or clarifying what 'unique matching window' means operationally (error on multiple matches?).

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?

The word 'Wait' plus the fullscreen/fills_display triggers implies usage when a window must reach a state rather than merely exist, but there is no explicit when-to-use vs. kde_window_find, kde_window_inspect, or kde_window_activate, and no stated prerequisites or failure handling.

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