Resolve Slack message or Zendesk ticket URLs into conversation references for a specified agent_id, mapping external support threads to ElevenLabs agent resources.
Resolve Conversation Reference
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | Agent id (agent_…) or speech engine external id (seng_), resolved to the same underlying resource. | |
| reference | Yes | A Slack message URL or a Zendesk ticket URL. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false, which already carries the safety profile. The description adds nothing beyond that — notably it does not disclose that resolution depends on an external Slack/Zendesk lookup (openWorld), nor what a resolution yields. With annotations the bar is lower, but this still contributes zero behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
It is short, but under-specification rather than genuine conciseness — a single title fragment carrying no information. There is nothing to waste, but also nothing earning its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-required-param resolver with no output schema, the description should at least say what resolution produces (conversation id? route?). It leaves the agent to infer everything from the name and schema, which is inadequate even though the schema itself is well documented.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%: the schema already explains that agent_id accepts agent_… or seng_ ids and that reference is a Slack message URL or Zendesk ticket URL. Per the rubric, full coverage sets baseline 3; the description adds no extra parameter meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description is the bare title 'Resolve Conversation Reference' — a restatement of the name that adds no verb specificity, no resource explanation, and no differentiation from siblings like get_conversation_* or the many *_route tools. An agent cannot tell from this text what 'resolving a reference' actually does or returns.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No when-to-use guidance, no prerequisites, and no alternatives named. The agent has no cue for choosing this over the ~300 sibling conversation/route tools, or when a Slack/Zendesk reference should be resolved at all.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.