preview_reconnect_linkedin_accountDry-run of re-authenticating a LinkedIn account. Explains the side-effects without doing anything. ALWAYS call this first — reconnecting changes the account id upstream and can orphan existing outreach history.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the safety burden, and it does so clearly: 'without doing anything' states the dry-run is non-mutating, and the warning about changed account id and orphaned outreach history adds useful risk context. It could go further by describing the exact output, but that is not critical for a dry-run tool.
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?
The description is two sentences, front-loaded with the definition and followed by the critical usage warning. There is zero filler, and every sentence adds distinct value.
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 one-parameter dry-run tool, this is nearly complete: it covers what the tool does, that it is safe, and why it must precede reconnection. It does not spell out the meaning of id in text or enumerate which side-effects are explained, so a bit more detail would make it fully self-contained.
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?
The input schema has one undocumented id parameter with 0% coverage, so the description must supply meaning. It implies the id identifies the LinkedIn account being reconnected, but it does not explicitly state 'id is the LinkedIn account id' or add format details beyond the schema's string type. The single-parameter context makes this minimally adequate, but not more.
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 uses a specific verb, 'Dry-run', and a clear resource, 're-authenticating a LinkedIn account', while explicitly stating it explains side-effects without doing anything. This clearly distinguishes it from the actual reconnect_linkedin_account sibling and other LinkedIn connection tools.
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?
The imperative 'ALWAYS call this first' gives an explicit trigger and explains the consequence ('can orphan existing outreach history'). It does not explicitly name reconnect_linkedin_account as the follow-up action or state when this preview is unnecessary, though the sibling list makes that inferable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Despite consistently detailed descriptions, several tool pairs have unclear boundaries: `get_subscription_limits` and `get_agent_plan_limits` describe essentially the same agent-slot check, `crm_get_conversation` and `crm_communication_thread` both claim to return the full message thread, and `get_credit_usage_by_agent` vs `get_credit_usage_for_agent` differ only by preposition. At 149 tools, an agent will regularly misselect between these near-duplicates.
The dominant pattern is verb_noun with domain prefixes (`crm_*`, `sdr_*`) and a consistent `preview_*` family that maps cleanly to destructive/expensive actions. Deviations are minor but real: CRM deletes use the inverted `delete_crm_*` form while other CRM ops use `crm_*`, and credit-usage tools mix `by_agent`/`for_agent` prepositions.
149 tools is nearly three times the 50+ threshold the rubric treats as extreme, even though the platform genuinely spans agents, campaigns, audiences, CRM, SDR, billing, and connections. Many could be consolidated without losing capability — e.g. the 11 balance/credit-usage tools, the two LinkedIn-account listers, and the 15+ preview variants.
The surface is remarkably complete: full CRUD/lifecycle coverage for agents, campaigns, audiences, CRM leads/stages, and SDR searches, plus billing, analytics, and connection management. Destructive or costly operations all have preview/approval counterparts, so there are no dead ends. If anything the risk is over-coverage rather than gaps.