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

With no annotations, the description carries the full burden and does well: it discloses the write nature, that null clears the mapping, and the authorization requirement ('Owner or office, or their agent'). It omits overwrite behavior when a ref already exists and any failure modes for an unknown id.

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 tight sentences; purpose first, the null-clearing rule and authorization note follow. No filler.

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?

Output schema exists, so return values need no explanation, and the mutation/clearing/authorization basics are covered. For a 5-param mutation with zero schema documentation, the unresolved id-vs-external_id ambiguity and undocumented shop_id leave an agent guessing on required inputs.

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 0% across five required params, so the description must compensate. It adds real meaning for external_id (null clears), system ('like quickbooks'), and the kind values, but leaves id and shop_id entirely unexplained and blurs the distinction between the internal id and external_id.

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?

A precise verb+resource: it records an outside system's id for one of four entity kinds so the sync updates rather than duplicates. That makes it clearly distinct from sync_findRefs and sync_changes in intent, though no sibling is named 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?

Gives the core usage context (external sync de-duplication) and an explicit null-to-clear rule. It does not point at sync_findRefs for lookup-first workflows or state what to do if a conflicting ref already exists, so alternatives are only implied.

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