Skip to main content
Glama

Find contacts

list_contacts
Read-onlyIdempotent

Find the people in the user's conversations by a name or a phone number the user gives, one entry per person, the most recently active first. Each entry carries the person's name, their phone number in E.164 (null when Werify does not know it, as in a .zip import), how many messages they sent, and the 10 most recent conversations they appear in, whose conversation_id the read tools take, with conversation_count for all of them. query is the name (case- and accent-insensitive) or the phone number to look for, and phone, one of the user's connected numbers, keeps that number's conversations; large lists page with cursor. These are the people seen in the user's archive, not the phone's address book. Only conversations the user owns or has been shared are accessible.

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": {
      "query": "<query>"
    },
    "name": "list_contacts"
  }
}

Input Schema

NameRequiredDescriptionDefault
phoneNoOptional: one of the user's connected numbers, as list_connected_numbers returns it. Lists only the people of that number's conversations; omit it for every conversation, imported ones included.
queryYesThe name or phone number to look for. A name matches as a case- and accent-insensitive substring; a number matches on its digits.
cursorNoThe next_cursor from a previous page, sent with the query again; the cursor keeps the query and phone it was made with.

Output Schema

NameRequiredDescriptionDefault
contactsNo
next_cursorNoPass back as cursor to get the next page; null on the last page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / cursor / description
      Previous value: -"The next_cursor from a previous page; it carries the query and phone with it."New value: +"The next_cursor from a previous page, sent with the query again; the cursor keeps the query and phone it was made with."
    • changedInput schema / properties / query / description
      Previous value: -"Optional name or phone number to look for. A name matches as a case- and accent-insensitive substring; a number matches on its digits."New value: +"The name or phone number to look for. A name matches as a case- and accent-insensitive substring; a number matches on its digits."
    • addedInput schema / required
      Added value: +[
      +  "query"
      +]
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description still adds real behavior: result ordering by recency, the null E.164 case with its cause (`.zip` import), the per-person cap of 10 conversations alongside the full `conversation_count`, and cursor-based paging for large lists. Fields of each entry are also enumerated, which is partly redundant with the existing output schema, keeping it from a 5.

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

Conciseness3/5

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

The purpose and ordering are front-loaded, which is good, but the single dense paragraph re-explains `query`, `phone`, and `cursor` in terms the schema already uses, and the per-entry field list overlaps the output schema. Nothing is filler exactly, but several clauses duplicate structured data rather than adding to it.

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?

For a filtered list tool with three parameters and an output schema, the description covers ordering, paging, null handling, field contents, and permission scoping. An agent has everything needed to call it correctly and to interpret what comes back without opening another tool.

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

Parameters3/5

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

Schema coverage is 100%, so all three parameters are already documented with matching detail (case/accent-insensitive substring, digit matching, cursor retaining query and phone). The description restates `query`, `phone`, and `cursor` semantics without adding new meaning beyond the schema, so the baseline 3 applies.

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 description opens with a specific verb and resource ("Find the people in the user's conversations") and pins down scope, entry granularity ("one entry per person"), and ordering ("most recently active first"). The closing line "These are the people seen in the user's archive, not the phone's address book" disambiguates it from a superficially similar address-book lookup.

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?

It states the triggering input ("a name or a phone number the user gives") and an explicit exclusion (archive contacts, not the device address book), plus an access constraint ("Only conversations the user owns or has been shared are accessible"). It stops short of naming any alternative tool for the case where the agent wants messages rather than people, so a 4 rather than a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources