Skip to main content
Glama

delete_contact

DestructiveIdempotent

Deletes a contact only after explicit confirmation, returning a full copy and arguments to recreate it; refuses if notes or linked cards exist.

Instructions

Delete a contact. It needs 'confirm' true. Without it, nothing is deleted, and the result shows the contact (name, emails, phones) so you can ask the user. The result of a delete has a full copy of the contact in 'contact', and in 'recreate' the arguments for create_contact, so the contact can be made again. Notes are not copied, because the app cannot read them. macOS refuses to delete a contact that has a note, unless the app has a special Apple entitlement. Then the tool returns an error and nothing changes. A contact linked from several cards (for example iCloud and Gmail) is refused: delete it in the Contacts app.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "delete_contact"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesContact id from search_contacts. Use it as given.
confirmNoMust be true to delete the contact. Without it, nothing is deleted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already mark it destructive and idempotent, but the description goes far beyond them: it explains the confirm gate and what happens without it, the shape of the returned data ('contact', 'recreate'), that notes are not copied, and two distinct refusal conditions with an entitlement caveat. This is exactly the kind of behavioral context annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and the confirm requirement, with each subsequent sentence carrying distinct information about results, limitations, and refusals. There is mild redundancy ('Without it, nothing is deleted' duplicates the schema text) but nothing that could be cut without losing substance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must explain return values — and it does, naming the 'contact' and 'recreate' fields and their purpose. Combined with the failure modes and entitlement caveat, an agent has everything needed to call this correctly and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented, which sets a baseline of 3. The description nevertheless adds real meaning: it explains the purpose of 'confirm' (safety gate) and that the failed-confirm result returns the contact details specifically so the agent can prompt the user, which the schema's terse line does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb and resource ('Delete a contact') and immediately layers on the two-phase confirm requirement, so the agent knows both the action and its guard. It is unmistakably distinct from get_contact, update_contact, and the non-contact delete_* siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description spells out the situations where deletion is refused (contact has a note, contact is linked across multiple cards) and redirects the user to the Contacts app for the linked-card case, which is actionable routing guidance. It does not explicitly contrast with other in-app siblings, but the resource is unambiguous enough that this is a minor gap.

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