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

Annotations already declare the mutation profile (readOnly=false, destructive=false, idempotent=true), so the bar is lower. The description still adds real content beyond them: the typeLocked in-place restriction, the fact that returned IDs/option IDs are immediately reusable without a metadata reread, and the routing to copy_column for conversion. It does not discuss failure modes of the enrichment prompt itself.

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 sentences with the purpose front-loaded, then operational guidance, then the sibling escape hatch. Dense but each sentence earns its place. The first sentence is a long enumeration that could be tightened, keeping it short of a 5.

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?

An output schema exists, so return values need not be explained, and the description correctly focuses on mutation semantics, the typeLocked limitation, and ID reuse. The idempotency contract is left to the annotation and the idempotencyKey schema field rather than being discussed, which is a minor gap for a tool with 9 required parameters.

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 only 33% and several parameters (prompt, formatInstructions, contextColumnIds) carry no schema description at all, so the description has to compensate — and it does, naming enrichment prompt, output-format instructions, context-column scope, select options, and placement. That maps most of the 9 parameters to meaning beyond the raw schema, though it does not describe idempotencyKey or the constraint interplay between type and optionLabels.

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?

"Add one fully configured column" gives a specific verb+resource, and the enumerated sub-capabilities (enrichment prompt, output-format instructions, context-column scope, select options, placement) tell the agent exactly what 'fully configured' means. The closing sentence explicitly carves out the boundary with sheets_copy_column, so it is distinguishable from a 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?

It names an alternative and the condition selecting it: a typeLocked column cannot change type in place, so use sheets_copy_column for conversion. It also gives workflow guidance (reuse returned IDs/option IDs, no metadata reread). However it offers no guidance for the more likely comparison set — sheets_update_column, sheets_rename_column, sheets_change_column_type — so exclusions are incomplete.

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