Update a customer

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

Annotations already declare the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds substantial behavior beyond that: metadata is merged rather than replaced, setting a key to "" deletes it, merged metadata is capped at 50 keys, and the specific error codes returned on collision or overflow. That is exactly the operational context an agent needs before invoking a mutation.

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 tight sentences: the restated title line is mildly redundant but acts as an anchor, then merge semantics, then error conditions — ordered from core behavior to edge cases. No filler and no repetition of schema-only details.

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 six-parameter mutation with no output schema, the description covers the non-obvious parts: merge behavior, deletion sentinel, key cap and error codes. It does not say what the response contains or whether unspecified fields are left untouched, which is the one remaining gap for an update tool.

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 only 50% (name, email and phone have no schema descriptions), and the description compensates by naming those three updatable fields and by explaining metadata's merge-and-delete semantics plus its size limit. It says nothing extra about idempotency_key, but the schema already documents that parameter fully, so the gap is minor.

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 opens with a specific verb+resource ('Update a customer') and immediately narrows the scope to the mutable fields ('email, name or phone'), which makes it distinguishable from create_customer and get_customer in the sibling list. It stops short of naming any sibling explicitly, so it is clear rather than maximally differentiating.

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 by the verb — an agent can infer this is the tool for modifying an existing customer, but the description never states prerequisites, when to prefer it over other write paths, or what happens on a partial update. The error cases (409 customer_exists, 400 metadata_too_large) are useful context but are failure modes, not when-to-use guidance.

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