Skip to main content
Glama
wazap-mcp

wazap-mcp

by razvangirgiz

Find who the user means

find_contact
Read-onlyIdempotent

Resolve who a name, nickname, number or ID refers to before drafting. Returns the matching chat_id with number, note, tags and context, or flags ambiguity so you ask instead of guessing.

Instructions

Who a name, nickname, relationship ("mama"), filed detail ("AP-123"), group, number or id means, before drafting. resolved: contact.chat_id, with number, note, tags, details and, when writing, context. ambiguous or not_found: ask the user; never guess. Several accounts: see fix. tag: its people.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
tagNoList everyone filed under this tag instead
kindNoany
nameNoWhat the user calls them ("Ana", "mamei"), a number or an id
limitNoAmbiguous: at most 5 per account; a tag list: up to 50
qualifierNoTells two apart: "contabilitate", a group, the last 4 digits
account_idNo
include_contextNoRecent messages and the user's style (write sessions)

Output Schema

NameRequiredDescriptionDefault
fixNoWhat to do next, when not resolved
nextNoResolved: how a message to them starts
notesNoCaveats to act on or tell the user
queryYes
statusYes
closestNoOnly when not_found
contactNoOnly when resolved
contextNoOnly when resolved, in a session that can write: what a draft to them is written after
omittedNoOnly when listed and cut by limit: how many more on each account
contactsNoOnly when listed: everyone filed under the tag
can_draftNoResolved in a session that cannot send
account_idNoThe account that answered; null when several accounts were searched and none answered alone
candidatesNoOnly when ambiguous; best first
accounts_searchedNo
accounts_unavailableNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed26 schema fields changedv1.7.4
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / include_context / description
      Previous value: -"Recent messages and the user's style, when resolved in a write session"New value: +"Recent messages and the user's style (write sessions)"
    • changedInput schema / properties / name / description
      Previous value: -"What the user calls them (\"Ana\", \"mamei\", \"fotbal\"), or a number or id"New value: +"What the user calls them (\"Ana\", \"mamei\"), a number or an id"
    • removedOutput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • addedOutput schema / properties / candidates / items / properties / groups_in_common / properties / count / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / candidates / items / properties / groups_in_common / properties / count / minimum
      Added value: +-9007199254740991
    • removedOutput schema / properties / candidates / items / properties / matched / $ref
      Removed value: -"#/properties/contact/properties/matched"
    • addedOutput schema / properties / candidates / items / properties / matched / additionalProperties
      Added value: +false
    • addedOutput schema / properties / candidates / items / properties / matched / properties
      Added value: +{
      +  "class": {
      +    "description": "exact, word, diminutive, prefix, substring or fuzzy",
      +    "type": "string"
      +  },
      +  "source": {
      +    "description": "What matched: name, nickname, relatie, tag, field, note, business_name, notify, push_name, group_name",
      +    "type": "string"
      +  },
      +  "value": {
      +    "type": "string"
      +  }
      +}
    • addedOutput schema / properties / candidates / items / properties / matched / required
      Added value: +[
      +  "source",
      +  "value",
      +  "class"
      +]
    • addedOutput schema / properties / candidates / items / properties / matched / type
      Added value: +"object"
    • addedOutput schema / properties / candidates / items / properties / messages_90d / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / candidates / items / properties / messages_90d / minimum
      Added value: +-9007199254740991
    • removedOutput schema / properties / closest / items / $ref
      Removed value: -"#/properties/candidates/items"
    • addedOutput schema / properties / closest / items / additionalProperties
      Added value: +false
    • addedOutput schema / properties / closest / items / properties
      Added value: +{
      +  "account_id": {
      +    "description": "Set when several accounts were searched",
      +    "type": "string"
      +  },
      +  "business": {
      +    "type": "boolean"
      +  },
      +  "groups_in_common": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "count": {
      +        "maximum": 9007199254740991,
      +        "minimum": -9007199254740991,
      +        "type": "integer"
      +      },
      +      "names": {
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      }
      +    },
      +    "required": [
      +      "count",
      +      "names"
      +    ],
      +    "type": "object"
      +  },
      +  "kind": {
      +    "enum": [
      +      "person",
      +      "group"
      +    ],
      +    "type": "string"
      +  },
      +  "last_exchanged": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "ago": {
      +        "type": "string"
      +      },
      +      "at": {
      +        "type": "string"
      +      },
      +      "direction": {
      +        "enum": [
      +          "sent",
      +          "received"
      +        ],
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "at",
      +      "ago",
      +      "direction"
      +    ],
      +    "type": "object"
      +  },
      +  "matched": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "class": {
      +        "description": "exact, word, diminutive, prefix, substring or fuzzy",
      +        "type": "string"
      +      },
      +      "source": {
      +        "description": "What matched: name, nickname, relatie, tag, field, note, business_name, notify, push_name, group_name",
      +        "type": "string"
      +      },
      +      "value": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "source",
      +      "value",
      +      "class"
      +    ],
      +    "type": "object"
      +  },
      +  "messages_90d": {
      +    "description": "The user's own messages to them in the last 90 days",
      +    "maximum": 9007199254740991,
      +    "minimum": -9007199254740991,
      +    "type": "integer"
      +  },
      +  "name": {
      +    "type": "string"
      +  },
      +  "name_source": {
      +    "enum": [
      +      "contact",
      +      "nickname",
      +      "business",
      +      "pushname",
      +      "group",
      +      "none"
      +    ],
      +    "type": "string"
      +  },
      +  "note": {
      +    "description": "What the user noted about them",
      +    "type": "string"
      +  },
      +  "number_tail": {
      +    "description": "Last 4 digits of the number; the full number is never given for a candidate",
      +    "type": "string"
      +  },
      +  "score": {
      +    "type": "number"
      +  },
      +  "tags": {
      +    "items": {
      +      "type": "string"
      +    },
      +    "type": "array"
      +  },
      +  "waiting": {
      +    "additionalProperties": false,
      +    "description": "Set when an ask of theirs is still open, as catch_up reads it: when they asked, still unanswered",
      +    "properties": {
      +      "ago": {
      +        "type": "string"
      +      },
      +      "since": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "since",
      +      "ago"
      +    ],
      +    "type": "object"
      +  }
      +}
    • addedOutput schema / properties / closest / items / required
      Added value: +[
      +  "kind",
      +  "name",
      +  "name_source",
      +  "messages_90d",
      +  "matched",
      +  "score"
      +]
    • addedOutput schema / properties / closest / items / type
      Added value: +"object"
    • addedOutput schema / properties / contact / properties / fields / propertyNames
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / contacts / items / properties / fields / propertyNames
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / context / properties / style / properties / basis / properties / days / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / context / properties / style / properties / basis / properties / days / minimum
      Added value: +-9007199254740991
    • addedOutput schema / properties / context / properties / style / properties / basis / properties / own_messages / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / context / properties / style / properties / basis / properties / own_messages / minimum
      Added value: +-9007199254740991
    • addedOutput schema / properties / omitted / items / properties / count / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / omitted / items / properties / count / minimum
      Added value: +-9007199254740991
  2. Changed1 schema field changedv1.6.0
    • removedInput schema / properties / account_id / description
      Removed value: -"Account id"
  3. Addedv1.0.3

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so credit goes to what the text adds: the tiered outcome model (resolved vs. ambiguous vs. not_found), the instruction to ask the user rather than guess, and the pointer to the account-fix path for multi-account setups. That is real behavioral content an annotation cannot express.

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?

It is short with no filler, and the core purpose comes first, but the telegraphic fragments ('resolved: contact.chat_id, with number, note, tags, details and, when writing, context') are near-ungrammatical and force re-parsing. Brevity here costs comprehension rather than buying it.

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

Completeness4/5

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

For a 7-parameter, zero-required lookup with annotations and an output schema, the description covers the important unknowns: what counts as a match, what happens on ambiguity, and the multi-account escape hatch. Return-value detail is partly redundant given the output schema, and per-parameter limits are left to the schema, but nothing essential to calling it correctly is absent.

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?

With 71% schema coverage the baseline is 3. The text does add meaning for a few parameters — the accepted forms of 'name' (nickname, relationship, filed detail, number, id), the meaning of 'tag' as a list-everyone mode, and the implicit 'context when writing' for include_context — but 'qualifier', 'limit' and 'kind' are left entirely to the schema, so it only partially extends the structured data.

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

Purpose3/5

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

The description conveys that this resolves a loose reference (name, nickname, "mama", "AP-123", group, number, id) to a contact, and the scope hint 'before drafting' situates it. But it is written as a noun fragment with the verb buried ('Who ... means'), so the agent must reconstruct 'look up / disambiguate a contact' rather than reading a clean verb+resource statement. No sibling is named for contrast.

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?

'before drafting' gives a concrete trigger, and 'ambiguous or not_found: ask the user; never guess' plus 'Several accounts: see fix' route the agent to the correct follow-up when the lookup is inconclusive. What is missing is an explicit negative case (e.g. when to use list_contacts or search instead of this resolver).

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