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

Goes well beyond the annotations by disclosing the read-modify-write internals, that the vendor performs a full PUT, and the resulting lost-update race window. That is exactly the operational context an agent needs before mutating a customer, which the annotations alone (readOnly=false, destructive=true, idempotent=true) cannot convey.

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?

Front-loads the write/partial-update constraint, then adds the safety caveats and the endpoint tag in dense, waste-free sentences. Every clause adds actionable information.

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?

No output schema exists, and the description thoroughly covers mutation semantics and side effects, but it leaves return-value behavior and per-field meaning unaddressed for a 21-parameter tool. Mostly complete for correct invocation, with a minor gap on what comes back.

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?

With 21 parameters and only 29% schema description coverage, the description carries real weight by explaining the partial-update semantics (only supplied fields change, others preserved via the internal read). However, it says nothing about individual field meanings, formats, or the customer_group_id/customer_code references, leaving much of the parameter surface undocumented.

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?

Opens with an explicit 'WRITE: change fields of an existing customer', naming the verb, resource, and mutation class, plus the underlying endpoint PUT /customers/{customer_id}. This clearly distinguishes it from create_customer and get_customer siblings.

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?

Clearly frames this as a partial-field update where only passed fields change, and states what it cannot do (delete, change balances). It doesn't explicitly name sibling tools as alternatives (e.g., create_customer for new records), so it stops just short of full routing guidance.

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