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

Annotations already declare destructive/idempotent/non-read-only, but the description adds substantial context the annotations cannot: the two-phase preview-then-apply contract, that a no-token call changes nothing and returns a preview payload, token expiry and single-use semantics, stale_revision handling, and replays returning replayed: true instead of double-applying. It is consistent with idempotentHint=true and destructiveHint=true, and adds an untrusted-content warning.

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 surface, then the confirmation protocol in logical order; almost every clause carries operational meaning. It is on the verbose side with some restatement around 'preview again' and repeat approvals, but not padding for its own sake given the safety stakes.

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 compensates by describing preview contents (summary, changes, warnings, token) and post-apply results (status applied, replayed, change ids), plus the stale_revision failure path. It stops short of enumerating other error behavior and does not restate the multi-workspace requirement, but an agent has enough to act 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 only 43%, so the description must carry weight, and it does: it enumerates the mutable fields and clarifies that active is a re-activation switch rather than a free boolean, and it expands confirmationToken semantics well beyond the schema's one-liner. It does not mention workspaceId or fieldId sourcing, leaving part of the gap unpatched.

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?

The opening sentence names a specific verb and resource plus the exact mutable surface (label, description, required, active: true). It also draws an explicit boundary that separates it from create_custom_field/delete_custom_field: standard fields cannot be changed here.

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 prescribes the precise call sequence (first without confirmationToken, then with it after user approval in the same turn), defines what does not count as approval, and states the exclusion for standard fields. The agent knows when to call, when not to, and what gates the mutation.

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