Modify beams

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

Goes well beyond the annotations: discloses that changes are a single undo step, that only supplied fields change (partial patch semantics), that values are validated like create_beams, that non-beam GUIDs are rejected per item, and the exact return shape [{guid}|{error}] in input order. Annotations only gave the safety profile; the description adds real behavioral detail.

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-loaded with the core action and the undo-step qualifier, then dense but purposeful specifics. It is long-ish for a description, yet nearly every clause carries distinct functional information (return shape, hole modes, segment scoping), so little is wasted.

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?

With no output schema, the description supplies the return contract and error behavior; with open-world nested patch objects, it supplies the field vocabulary via create_beams and the segment/hole semantics. An agent has everything needed to call it correctly.

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%, but the description still adds meaning the schema cannot: the top-level section/surface fields apply to ALL segments, 'segments' takes the full list with {} meaning unchanged, and holes/addHoles/removeHoles define distinct replace/append/delete semantics. This is substantive parameter semantics beyond structured fields.

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?

'Changes existing beams' states a specific verb and resource, and contrasting it with create_beams' field set makes clear this is the mutation counterpart. The agent can distinguish it from create_beams, modify_columns, and modify_elements without opening a 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?

It gives concrete operational guidance: 'Read the current values first with get_element_details', and spells out the choice between top-level fields and 'segments' as well as the three hole strategies (holes/addHoles/removeHoles). It does not explicitly exclude scenarios where a generic modify_elements would be preferred, so it stops short of full when/when-not routing.

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