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

Annotations are minimal (readOnlyHint false, destructiveHint false), so the description carries the burden. It discloses that the operation requires Accessibility permission, which is not in annotations, and that it returns the actual post-constraint bounds. It explains the persistence implication ('every take is framed identically across runs'), adding behavioral context beyond the schema. No contradiction with annotations.

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, zero filler. The first sentence states the action and its purpose; the second covers the return value and permission requirement. The most important information is front-loaded, and every word earns its place.

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 two-parameter tool with a nested object and no output schema, the description is largely complete. It explains the action, the return value, the permission prerequisite, and the intended use. Minor gaps: it does not explicitly state that window_id comes from list_windows (though the schema does), and it does not elaborate on coordinate system details. However, given the schema coverage and annotations, nothing critical is missing.

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 schema already fully describes both parameters: window_id as 'Window to move or resize, from list_windows' and bounds as '{x,y,w,h} global points.' The description restates this information without adding new semantics (e.g., coordinate origin, constraints, or units beyond 'global points'). Since schema coverage is 100%, the baseline is 3; the description adds no extra meaning.

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 a specific verb ('Pins'), the resource (a window identified by window_id), and the effect (fixed bounds in global points). It distinguishes itself from siblings like window_focus (which focuses) and list_windows (which enumerates) by describing the pinning action and the consistency goal across runs.

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 description provides clear context for when to use it: when consistent framing across runs is needed. It does not explicitly mention alternatives or exclusions, but the context is unambiguous. It also notes a prerequisite (Accessibility permission), which guides usage. No explicit when-not-to-use is given, but the purpose is specific enough.

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