Convocore

notifications_read

Read-onlyIdempotent

Your notifications inbox: things that changed outside this conversation. Today: Meta review results for WhatsApp templates (APPROVED / REJECTED / PAUSED / DISABLED, with the rejection reason). Check it at the start of a session and after submitting or editing a template, instead of polling every template. Mark items handled with notifications_write. Actions: list — unread WhatsApp template review results, newest first

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": {
      "action": "<action>"
    },
    "name": "notifications_read"
  }
}

Input Schema

Name	Required	Description
`mode`	No	compact (default) = light mode: long text is cut and bulky blobs are replaced by a size marker. full = complete API response.
`limit`	No	Default 50, max 100. Newest first.
`action`	Yes
`agentId`	No	Only this agent. Omit for the whole workspace.
`includeAcknowledged`	No	Also return items already marked as handled. Default false (unread only).

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 31, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is in what the inbox contains (APPROVED/REJECTED/PAUSED/DISABLED with rejection reason), the default unread-only behavior, and how items get cleared via notifications_write. It stops short of describing volume or retention behavior, but the workflow semantics are well covered.

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-loads the identity of the inbox before the operational advice, and each sentence carries new information (contents, timing, clearing, action). It is one long run-on paragraph rather than clearly segmented lines, which slightly hurts scanability.

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?

With five parameters, rich annotations, and no output schema, the description supplies the missing return-value shape (review statuses plus rejection reason) and the action list. Only the single allowed action and pagination edge cases are left to the schema, so an agent has enough to call it correctly.

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 80%, so mode, limit, agentId and includeAcknowledged are already documented. The description only echoes 'newest first' and 'unread ... results,' which duplicate existing limit/includeAcknowledged descriptions without adding format or filtering nuance; 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?

Names the resource (notifications inbox) and defines its scope precisely: 'things that changed outside this conversation,' with today's content being Meta WhatsApp template review results. It is instantly distinguishable from notifications_write (mark handled) and whatsapp_templates_read (per-template polling), which it explicitly says to avoid.

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

Usage Guidelines5/5

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

Gives explicit when-to-use timing ('at the start of a session and after submitting or editing a template') and names the alternative it replaces ('instead of polling every template'). The exclusion plus the handoff to notifications_write for state changes leaves little to infer.

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

All Convocore tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?