set_customer

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

With no annotations, the description carries full burden. It does add one important fact (apply is currently unavailable) and implies dryRun defaults to true, but omits critical traits for a mutation tool: auth/permission requirements, reversibility, and what a preview returns. The 'split-brain preview/apply' behavior is only hinted at.

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 workflow framing, no wasted fluff. But it spends its limited budget on deprecation/roadmap context rather than actionable invocation detail.

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 10-parameter mutation tool with no annotations, no output schema, and a non-trivial preview/apply state machine, the description is far short. It never explains the required call sequence, defaults, or the concurrency/hash parameters the agent must supply.

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% with 10 parameters, several non-obvious: previewToken, idempotencyKey, and three expected*Hash fields, expectedEntityTimestamp, dryRun, mode. The description mentions none of them, so an agent cannot know that apply requires a previewToken or how the expected hashes act as optimistic-concurrency guards.

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 calls this a 'Preview-first replacement for the deprecated immediate customer write,' which hints at a preview workflow but never states the core purpose clearly: setting/updating a customer record. It frames itself relative to a deprecated tool instead of stating verb+resource. An agent must infer that this is the customer-write path.

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 implies preview-first behavior and says 'Apply remains unavailable until its domain adapter and canary are complete,' but gives no explicit when-to-use vs alternatives, no guidance against the sibling upsert_customer, and no explanation of how previewToken chains into the apply flow.

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