Create or update a contact by phone number. WARNING: if a contact with this phone number already exists, its name/notes will be overwritten (upsert semantics). ALWAYS confirm the change with the user before calling. Use search first to check if the contact exists.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | Yes | Notes about the contact | |
| lastName | Yes | Last name of the contact | |
| firstName | Yes | First name of the contact | |
| phoneNumber | Yes | Phone number of the contact |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and readOnlyHint=false, but the description earns credit by specifying exactly what is destroyed: existing name/notes are overwritten. That is concrete consequence detail the annotations cannot convey. It stops short of saying whether unmentioned fields are preserved or cleared, or what the response contains.
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?
Four short sentences, each carrying a distinct payload: purpose, destructive consequence, confirmation requirement, prerequisite check. The destructive warning is surfaced near the front rather than buried.
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?
With no output schema, annotations covering the safety profile, and full parameter documentation, the description covers nearly everything an agent needs before calling. The remaining gap is what a successful upsert returns and whether it reports create-vs-update, which would help the agent relay results to the user.
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 every parameter is already documented, and 3 is the baseline here. The description adds one genuinely new semantic point — phoneNumber is the matching key that determines create-vs-update — but says nothing about how notes interacts with the overwrite behavior.
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?
States a specific verb pair and resource ('Create or update a contact') plus the identity key ('by phone number'), and immediately clarifies that this is an upsert rather than a pure create. An agent can distinguish it from get_contact, update_contact and search without opening any schema.
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?
Explicitly prescribes two pre-call behaviors: 'Use search first to check if the contact exists' and 'ALWAYS confirm the change with the user before calling.' It names the alternative (search) but does not clarify when to prefer the sibling update_contact over this upsert path, which is the main unanswered routing question.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
