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

Annotations already supply the safety profile (destructiveHint=true), and the description adds genuinely useful behavior beyond that: partial-update semantics ('Only provided fields are changed'). However, the parenthetical '(reversible)' sits in tension with a destructiveHint of true and is not reconciled, so the signal is muddier than it should be. It also says nothing about auth scope or side effects of changing fields like email or payment_provider.

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 short, front-loaded clauses: what it does, the partial-update behavior, then the endpoint. No filler, no repetition of schema content.

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 9-parameter mutation tool with no output schema, the description covers the core mutation semantics and reversibility but omits what a caller gets back, permission/auth requirements, and any side effects of specific field changes. It is minimally sufficient rather than complete.

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 every one of the 9 parameters is already documented (formats, enums, nested metadata constraints). The description's only parameter-relevant statement is that unspecified fields are untouched, which is close to what the single required field already implies. Baseline 3 is warranted when the schema carries the load.

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 gives a specific verb and resource ('Updates an existing customer's details') and the underlying endpoint (PUT /customers/{customer_id}), which pins down exactly what happens. The verb alone cleanly separates it from the create/get/list siblings in the toolset.

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?

Usage is only implied: the agent must infer that this is the tool for modifying an existing customer rather than orb_create_customer, and no explicit alternative or precondition is named. 'Only provided fields are changed' is the one piece of actionable usage context, telling the caller it can send a sparse payload.

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