Undo Contact Change

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses meaningful behavior: reversibility is limited to certain change types, merges have a 30-day limit, and later edits cause rejection rather than overwrite. It also surfaces cost and authentication requirements. This adds significant operational 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?

Three dense sentences with no filler. The core action is front-loaded, followed by the most important special case and safety behavior. Every sentence earns its place.

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?

Given an output schema is present, the description need not detail return values. It covers scope, constraints, success-relevant behavior (rejection vs overwrite), cost, and auth. This is sufficient for an agent to call and interpret the result 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?

The schema leaves change_id undocumented, but the description explains its role and provides a special-case mapping for merges. Since request_id and idempotency_key already have schema descriptions, the description compensates well for the main gap.

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 description states a specific action—'Reverse a reversible contact_mutations row'—and enumerates the covered operations (rename, alias, identity, classify, link). This clearly distinguishes it from restore_* tools for events, expenses, trips, and cleanup.

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?

The description gives concrete usage context: how to handle merges (pass restore_id as change_id), the 30-day window, and the rejection behavior for later edits. It doesn't explicitly name alternatives or say when not to use it, but the scope and constraints are clear enough for an agent to select it appropriately.

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