wazap-mcp

Remember something about a person

remember

Idempotent

Store notes, tags, and details about contacts locally, keeping them off WhatsApp. Mark asks as handled and control privacy with #private and #no-catchup flags.

Instructions

Keep what the user says about someone, locally, never on WhatsApp: a note, tags, details find_contact matches ({"relatie": "mama"}), or handled: true for an ask dealt with elsewhere. #private keeps their words out of what you did not ask about them by name; #no-catchup keeps them out of catch_up.

Input Schema

TableJSON Schema

Name	Required	Description
`note`	No	"" removes it
`fields`	No	e.g. {"nickname": "Mișu", "role": "contabil"}; "" deletes a key
`chat_id`	Yes	Chat id, or a phone number
`handled`	No	Off catch_up's waiting until they write again
`add_tags`	No	e.g. ["client"]
`account_id`	No	Account id
`remove_tags`	No
`remove_fields`	No

Output Schema

TableJSON Schema

Name	Required	Description
`name`	Yes
`note`	No
`tags`	No
`fields`	No
`number`	No
`chat_id`	Yes
`handled`	No	The ask taken off the waiting list; null when nothing was open
`account_id`	Yes
`is_business`	No
`is_my_contact`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.0.3Sep 23, 2026

TDQS

A3.8/5.0

Behavior4/5

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

The description adds meaningful behavioral context beyond the annotations: data is stored locally and never on WhatsApp, and the '#private' and '#no-catchup' tags control future retrieval behavior. This is genuinely useful information that the annotations alone do not 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?

The description is compact and front-loads the core purpose before explaining special flags. It is slightly dense and could be more readable, but every part adds meaningful information without unnecessary filler.

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?

Given the output schema, 75% schema coverage, and annotations, the description covers the essential purpose, privacy behavior, and special handling for catch-up and private queries. The main gap is the lack of explicit differentiation from the 'learn' sibling, but the tool is still usable without that clarification.

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 already high at 75%, so the baseline is 3. The description adds value by giving concrete examples for 'details' ('{"relatie": "mama"}'), explaining 'handled: true' as marking an ask dealt with elsewhere, and clarifying the privacy/catch-up semantics of the special tags.

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

Purpose4/5

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

The description clearly identifies a specific action ('Keep what the user says about someone') and resource (person-related memory), and it adds important scope with 'locally, never on WhatsApp.' It also references the 'find_contact' and 'catch_up' contexts, which helps distinguish it from those siblings, though it does not explicitly contrast it with the 'learn' sibling.

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

Usage Guidelines3/5

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

The description provides useful context for when to set 'handled: true' and how '#private' and '#no-catchup' affect behavior, but it does not explicitly explain when to prefer this tool over alternatives like 'learn' or when not to use it. Usage is implied rather than directly stated.

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