get_chooser_column_values

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

Annotations already declare the safe read profile, but the description adds substantial non-obvious behavior: the per-column default is editor-only and returns null with a note outside an editor build while row values always resolve, out-of-range column_index is a reported error, and it confirms no compile/no save. These are exactly the caveats an agent needs and are not derivable from annotations or schema.

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 purpose and the sibling contrast, then caveats, then a compact return shape. Dense but every clause (editor-only default, error behavior, read-only guarantee) carries information; no filler sentences.

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?

No output schema exists, so the explicit Returns block meaningfully compensates by describing the returned object shape and the null default case. Combined with the editor-only and error caveats, an agent has enough to call it correctly; only minor gaps remain (no pagination/limit discussion, though row_count suggests full reads).

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% so the baseline is 3, and the description adds meaning beyond it: column_index semantics via the out-of-range error behavior, and the returns block clarifies how column_type, row_count and the typed cell shapes relate to the two inputs. It stops short of full extra detail but clearly exceeds the schema baseline.

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 (read) and resource (ONE COLUMN ACROSS ALL ROWS of a UChooserTable), then explicitly names the sibling get_chooser_row_values and contrasts the axis of access (column-wise vs one row across all columns). An agent can distinguish it from its closest sibling without opening either 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?

Names the alternative tool (get_chooser_row_values) and the distinguishing condition (read one column across all rows vs one row across all columns), which is clear actionable guidance. It stops short of an explicit 'use X when / avoid X when' statement for the other chooser siblings (evaluate/inspect), but selection is unambiguous for the primary fork.

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