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

Goes well beyond the annotations by clarifying that x/y/w/h/z_index are persisted column writes rather than a transient layout cache, and that kind/widget_key/content_ref are frozen and require delete-then-recreate to change. Not covered: partial-update semantics for unspecified fields and how the CONFLICT guard behaves (the latter is in the schema, not the description).

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, mutation behavior front-loaded, followed by the identity constraint and then the routing hint. Slight loss for the colloquial "through this door," which is understandable but less precise than the rest of the text.

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?

Annotations already cover the safety profile (writable, non-destructive, non-idempotent) and there is no output schema, so the remaining burden is on partial-update behavior and geometry units — neither is addressed. For a 10-parameter mutation tool, this leaves an agent guessing about what happens to fields it does not send.

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 only 20%, so the description carries a real burden; it does add meaning for the geometry params (real persisted writes) and effectively neutralizes the three identity params. However, it gives no units or coordinate-space semantics for x/y/w/h and no guidance on whether omitted fields are reset, leaving key gaps for a 10-param tool.

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 specific verbs (moves, resizes, restacks) against a specific resource (a surface already on the desk canvas) and implicitly scopes itself apart from desk_surface_create/delete/list/read by requiring an existing surface. An agent can tell exactly what operation this performs without opening the 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?

Explicitly gates usage on the surface already existing and gives a concrete next step ("NEXT: desk_surface_list to find the id to move"), which is real routing guidance. It does not explicitly name desk_surface_create as the alternative for new surfaces or warn against using this to change identity fields, but the exclusion is implied clearly.

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