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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false, so the safety profile is covered. The description usefully adds what actually happens (records move to the primary, then the duplicate is deleted), that it is reversible via unmerge, and that approval is required by default.

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 tight sentences, front-loaded with the trigger condition, followed by the effect, then the undo/approval notes. No filler, 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?

With annotations covering the safety profile and an output schema present, the description supplies the remaining essentials: when to invoke, what mutates, reversibility, and the approval requirement tied to the approval_id parameter. Nothing critical is missing.

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, but the description adds directional semantics by explaining that records flow to the primary contact and the duplicate is destroyed, which ties contact_id and duplicate_contact_id together conceptually beyond the field labels.

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 (merge) and resource (contacts) and immediately clarifies the scope: combining two contacts that are the same person. An agent can distinguish this from contacts.duplicates.find (detection) and contacts.unmerge (reversal) without opening a 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?

Gives a clear when-to-use trigger ('two contacts are the same person and the user wants them combined') and names the reversal sibling (unmerge). It does not, however, cross-reference the related contacts.duplicates.check/find tools that would precede a merge decision.

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