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

Annotations supply destructiveHint=true, and the description adds genuinely useful behavioral context beyond them: 'Only the fields you pass are sent' clarifies that this is a partial update that leaves unspecified fields intact, which resolves the PUT-replacement ambiguity, plus the underlying endpoint. It does not mention permission/auth requirements, but with annotations covering the mutation profile this is solid.

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 with zero waste; the partial-update constraint and the endpoint mapping are front-loaded and each sentence carries distinct 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?

For a 17-parameter mutation the description is thin: it neither mentions the breadth of updatable fields nor flags risky inputs, and with no output schema present it says nothing about what comes back. The partial-update note and endpoint are the right essentials, but a caller still has gaps around response and permissions.

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 the baseline is 3. The description names a few editable fields but adds no format, allowed-value, or default detail beyond what the schema already documents (enums for preferredLanguage/preferredContactMethod, bounds on discountPercent, etc.).

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?

Clear verb+resource ('Update a customer') with the category of editable fields named, and it is unambiguously distinct from create_customer, get_customer and update_order by sibling name alone. The field list ('name, address, note or preferences') is only a partial subset of the 17 schema properties, so the scope statement is slightly under-inclusive.

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?

There is no explicit guidance on when to use this versus alternatives such as create_customer, get_customer, or find_customers_by_*; the only hint is the required customerId in the schema. An agent gets no when/when-not framing or precondition (e.g., the customer must already exist).

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