Skip to main content
Glama

Telegram intake: Manage labels

intake_manage_labels
Destructive

Edit the caller's client labels. 'action': create (name, aliases, language) | update (label, name/aliases/language) | archive / unarchive (label) | add_target (label, tenant_id, entity_kind = crm_lead | erp_organization | erp_contact | erp_project, entity_ref, entity_title — the caller must belong to that workspace) | remove_target (label, target_id) | map_sender (label, key_kind = tg_user | tg_username | name | chat, key) | unmap_sender (sender_id). Only ever touches the caller's own labels. CONFIRMATION: this tool runs immediately when the caller asks for it — it writes only their own record, and they can undo it from this same surface, so the request is taken as the instruction. You get an ordinary result, not a plan_token. Everything destructive, outbound or financial still proposes and waits.

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": "intake_manage_labels"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNo
nameNo
labelNoA client label id, or its name/alias.
actionYes
aliasesNo
key_kindNo
languageNo
sender_idNo
target_idNo
tenant_idNo
entity_refNo
entity_kindNo
entity_titleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=false, and the description adds real context beyond them: the tool executes immediately, returns an ordinary result rather than a plan_token, is undoable from the same surface, and never touches other users' labels. The boundary against tools that 'propose and wait' is spelled out. The undo claim slightly softens the destructive annotation but does not contradict it.

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?

Dense but well-structured: the verb and scope lead, action variants follow in a piped list, and the confirmation policy closes. The final sentence about destructive/outbound/financial tools is slightly tangential but usefully delimits the immediate-execution rule.

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 13-parameter mutation tool with no output schema, the description covers action selection, per-action parameters, ownership scope, prerequisites, and confirmation behavior. It omits error/failure cases (unknown label, non-member workspace) and what the returned record contains.

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?

With only 8% schema coverage across 13 parameters, the description carries the load and does so by mapping conditionally-applicable parameters to each action (create takes name/aliases/language; add_target takes tenant_id/entity_kind/entity_ref/entity_title; unmap_sender takes sender_id). It does not explain the expected format or semantics of fields like entity_ref or key beyond their enum kinds.

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?

States a specific verb and resource ('Edit the caller's client labels') and then enumerates every action mode (create/update/archive/unarchive/add_target/remove_target/map_sender/unmap_sender). This clearly separates it from siblings like intake_list_labels or intake_assign_label without the agent needing to open any schema.

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?

Each action is bound to the parameters it uses, so an agent knows which mode to select for a given request, and the workspace-membership prerequisite for add_target is stated. It never names a sibling tool as an explicit alternative (e.g., 'to list labels use intake_list_labels'), so it stops short of full routing guidance.

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