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

Adds substantial context beyond the annotations: it discloses that the request may be clamped ('Returns the actual post-constraint bounds'), documents a specific failure mode and error code ('own_window'), and states the OS permission prerequisite (Accessibility). These are behaviors the destructiveHint/openWorldHint flags do not convey.

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?

Three tight sentences: effect first, then return value, then refusal case and permission. No filler or repetition; each clause carries distinct information.

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?

For a mutation tool with no output schema and only two required params, it covers effect, return, refusal, and permissions. Minor gaps remain: whether the 'pinning' persists (across app restarts or until another change) and what happens for an invalid window_id.

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 100%, and the description largely restates what the schema documents (bounds in global points, window_id). It confirms the point unit and that window_id comes from list_windows but adds no syntax or format detail the schema lacks, so the baseline 3 applies.

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 ('pins') and resource ('a window, by window_id') with the exact effect (fixed bounds {x,y,w,h} in global points) and the goal (identical framing across runs). This is clearly distinguishable from window_focus and list_windows, which are the nearest siblings.

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?

Explicitly names an exclusion and the alternative for it: 'Refuses LMCP's own windows... use web_show for those.' The use case ('so every take is framed identically across runs') gives context for choosing it. It does not contrast against window_focus or other window tools, so it stops short of full when/when-not coverage.

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