Shape set params

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

Annotations already establish the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds genuinely new behavior: downstream nodes recompute automatically, which is a side effect beyond the edited node and is not encoded in any annotation or schema field.

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?

One front-loaded sentence plus two compact examples; every element (scope, propagation semantics, call shape) earns its place with no filler.

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 2-parameter mutation tool with annotations and no output schema, this covers the mutation semantics and a couple of concrete call shapes. It leaves open which node types are valid targets and what happens on an unknown key or id, both of which the schema also fails to document.

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?

With only 50% schema coverage (the 'id' property is undocumented), the examples carry real weight: they show the id+params form, a geometry key ('r'), and a transform key ('translate:[1,0,0]'), which is not inferable from the schema alone. It doesn't explain valid key sets per node type, but it meaningfully compensates for the coverage gap.

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 ('change parameters of an existing node') and adds the key property that the model is parametric, so changes propagate downstream. It does not distinguish itself from the nearby sibling shape_edit_node, leaving the agent to infer the boundary between 'set params' and 'edit node'.

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 two inline examples imply the shape of a typical call, but there is no explicit when-to-use statement and no contrast with shape_edit_node, shape_transform, or shape_set_item_fds_props. Usage is inferable from the examples rather than stated.

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