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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), yet the description adds real value beyond them: partial-update semantics ('Only the fields passed change'), identity/link preservation, and a concurrency guard where out-of-band edits abort the apply. It doesn't mention auth scope or how the preview token/session persists, but the core behavior is disclosed.

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-loads the key fact (draft, returns a PREVIEW) in the first clause, then layers mutation semantics and the concurrency guard in short lines. Every sentence carries distinct information; nothing is repeated from the schema or annotations.

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 an output schema present and full parameter documentation, the description needn't explain returns or field shapes, and it correctly focuses on the preview/apply lifecycle. The remaining gap is the missing pointer to confirm_and_apply and to draft_call_asset, which matters given this tool's large sibling set.

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; the description earns an extra point by stating the partial-update contract ('Only the fields passed change'), which tells the agent omitted fields are preserved rather than reset — a non-obvious semantic the schema alone doesn't state globally.

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 and resource ('Draft changing a call asset in place') and immediately clarifies the output is a preview, not a committed change. The word 'in place' and 'changing' implicitly distinguish it from draft_call_asset (creation), but it never names that sibling, so an agent must infer the create-vs-edit split.

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 conveys the draft-then-apply workflow ('the preview shows the current values and pins them; an edit in Google Ads before the apply stops it'), which implies usage context. However, with ~140 siblings including draft_call_asset and confirm_and_apply, it never explicitly says 'use draft_call_asset to create a new number' or 'call confirm_and_apply to commit' — the routing is left implied.

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