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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the write nature is known; the description contributes the non-obvious limitation that support depends on the source system. However, it never clarifies whether the operation merges with or replaces existing metadata, which is the critical question for a destructive write, nor what happens when the source rejects the edit.

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 the action and the example front-loaded and the limitation trailing; nothing is padded. It could be tightened slightly by folding the example into a single parenthetical, but it reads efficiently.

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 destructive mutation with a nested free-form object and no output schema, the description covers the target and a source-side precondition but leaves merge-vs-replace semantics and failure behavior unaddressed. An agent can call it, but cannot confidently predict the result on a user that already has metadata.

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 50%: user_id is documented in the schema, but the metadata object has no schema description at all. The description compensates partially with the example { company: 'Acme' }, showing it is a free-form key/value map, but it does not say whether keys are arbitrary, whether values are typed, or whether omitted keys are removed.

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 states a specific verb and resource ("Set custom fields (metadata) on a user in their source system") plus a concrete example payload, which separates it from siblings like add_user_note or set_config. It stops short of naming the closest alternative, but the action is unmistakable.

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?

The clause "Only works where the source allows editing custom fields" gives a real precondition that helps an agent decide whether calling is worthwhile. There is no explicit when-to-use versus sibling guidance (e.g. versus add_user_note for free-text notes), so usage is only implied.

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