Modify columns

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

Goes well beyond the annotations (which only flag destructive/idempotent) by disclosing partial-failure behavior (returns [{guid} | {error}] in input order), per-item GUID rejection, validation parity with create_columns, the single-undo-step trait, and the segment-length side effect that changes the segment count. That is rich, tool-specific behavioral context.

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 mutation and its undo semantics, then the patch shape, then the segment/cuts rules. Dense parenthetical clauses make the middle sentences heavy, but every sentence carries required information and nothing is padding.

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?

Despite having no output schema, the description states the return shape per item, names the errors, and covers validation, undo, GUID filtering and segment semantics. For a mutation tool with sibling routing, nothing essential 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?

Schema coverage is 100% for declared params, but the meaningful payload fields live in the additionalProperties patch object, and the description carries them: the enumerable create_columns fields, the meaning of '{}' (= unchanged segment), what a different-length 'segments' list does, and how top-level section/surface/veneer fields fan out to all segments. This is decisive semantics the schema does not supply.

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+resource ('Changes existing columns') and immediately scopes it against siblings by linking to create_columns' field set and telling the agent to read values first via get_element_details. An agent can distinguish this from create_columns, modify_elements and the other modify_* tools 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?

Gives an explicit prerequisite ('Read the current values first with get_element_details'), explains which fields are valid (the create_columns set), and routes the agent between top-level vs 'segments' vs 'cuts' usage with the exact semantics of each. When-to-use and edge conditions are both covered.

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