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

Annotations already declare this as a non-readonly, non-destructive write, so the bar is lower. The description adds genuinely non-inferable context: required pair enforcement happens at the door, and rows are private to the creating user even though teammates share the tenant. It does not address duplicate pinning behavior, which matters given idempotentHint=false.

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?

Front-loads the action, then the branching rules, then the next step — a sensible order with little waste. The parenthetical aside about the schema not being able to express the pairing is mildly self-referential but does justify why the rule is stated here.

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 an 8-parameter creation tool with no output schema, the definition covers identity and branching but omits how the canvas position/size parameters behave — arguably the most error-prone part of a layout write. Nothing is wrong; the coverage is just partial.

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%, so the description carries the full burden. It explains the kind enum's two branches and the widget_key/content_ref pairing well, but leaves the five placement parameters (x, y, w, h, z_index) completely undocumented — no units, no coordinate origin, no 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?

States a specific verb and resource — pinning a widget or saved artifact onto the operator's home canvas — with a two-branch model (kind='widget' vs kind='artifact') that no sibling shares. The closing pointer to desk_surface_list makes the read/write split with its sibling explicit.

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?

Names the follow-up tool (desk_surface_list reads the current layout) and gives the conditional precondition for each kind, which is exactly the decision an agent needs before calling. It stops short of stating when to use desk_surface_update instead, or what happens if a key is already pinned.

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