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

With destructiveHint=true already declared, the description still adds real value by specifying the exact scope — it restores the most recently merged duplicate and moves back exactly what the merge moved, while records created after the merge stay. This edge-case disclosure goes beyond the annotations, though it doesn't note the single-use approval or irreversibility.

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?

Two sentences, front-loaded with the deciding scenario, with the behavioral detail following. Slightly dense due to the semicolon clause but 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?

An output schema exists so return values needn't be explained, and both params are covered in-schema. Purpose and behavioral scope are described; only the approval_id single-use semantics are left solely to the schema.

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 description coverage is 100%, so both contact_id and approval_id are already documented. The description adds no meaning beyond that, so the baseline of 3 applies.

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 (undo a merge by restoring the most recently merged duplicate and moving records back) that an agent can tell apart from contacts.merge. It's framed as a conditional 'when a merge was a mistake' scenario rather than a direct verb+resource statement, keeping it just short of a 5.

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 clearly states the triggering condition: 'When a merge was a mistake and the user wants it undone.' This gives concrete when-to-use context, though it never names the alternative (contacts.merge) or any exclusions.

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