Modify specific fields of an existing person record, changing only the fields you provide. Use it to update contact details, documents, or personal information without altering other data.
Change fields of an existing person. Only the fields you pass are changed.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| fields | Yes | Person fields; omit any you are not setting/changing |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden. It does disclose the key patch semantic — "Only the fields you pass are changed" — which is real behavioral value an agent could not otherwise know. It says nothing about permissions, what happens when id does not match a person, whether a field can be cleared (empty string vs. null), or whether the object is merged deeply or shallowly.
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, the mutation verb and resource front-loaded, and the patch semantics stated immediately after. No filler whatsoever.
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?
This is a mutation on a nested 26-field object with zero annotations and no output schema, so the description must supply the behavioral context itself. It does not state the return value (updated person or nothing), permission requirements, failure modes for a bad id, or how to unset a field — gaps that matter for a write operation of this shape.
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% and the nested fields object has 26 properties, several without descriptions. The description adds one meaningful clarification — that omitted fields are left untouched, so the object acts as a partial patch, not a replacement. The id parameter is left completely unexplained (internal vs. external identifier format), which is a notable gap.
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?
"Change fields of an existing person" gives a specific verb and resource, and the qualifier "existing" implicitly separates it from create_person in the sibling set. It does not name any sibling explicitly, so differentiation is left partly to inference.
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 second sentence implies this is the tool for partial modifications rather than full replacement, which is usable guidance. However, there is no explicit statement of when to prefer update_person over create_person, nor any prerequisite such as the person having to exist or be fetched first via get_person.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.