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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the write/mutation nature is covered. The description does add real value beyond them by disclosing that changes are logged and reversible, which softens the destructive hint meaningfully. However, it omits the behavior that matters most for an upsert with 9 all-optional fields: whether omitted fields are cleared or preserved on update, and what happens if a create is attempted with no name/email.

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 short sentences, zero filler, and the mode-switching rule is front-loaded where an agent will read it. It is arguably too terse for a destructive 9-parameter upsert, but nothing written is wasted.

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?

For a destructive upsert with no output schema and zero schema description coverage, the description is underspecified: it never says what a successful save returns, whether updates are partial or full-replacement, or how undo_action relates to it. The 'logged and undoable' note is the only behavioral anchor an agent gets.

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 0% across 9 parameters, so the description carries the full burden and largely fails to. It only clarifies that 'id' selects update mode; the other eight fields (name, email, phone, address, city, state, zip, company_name) get no explanation of format, mutual requirements, or which are needed to create a valid customer.

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 concrete verb+resource ('Add a customer, or update one by id') and, crucially, explains the create-vs-update switch that the name 'save_customer' alone would not convey. It is clearly distinguishable from the read-side sibling find_customer, though it never names that sibling explicitly.

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?

'or update one by id' implies the usage condition for each mode, which is more than nothing. But there is no guidance on when to prefer this over find_customer-first workflows, no prerequisites, and no pointer to the undo_action sibling that the 'undoable' claim depends on.

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