preview_buy_audience_setDry-run of purchasing an audience set — shows what would be bought and what it costs, WITHOUT spending credits. ALWAYS call this first and show the cost to the human.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Set id (UUID), not the slug |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and it discloses the most critical behavioral trait: no credits are spent. The term 'dry-run' plus 'shows what would be bought' communicates a non-committal preview. It does not discuss other side effects or permission requirements, but for this tool the no-cost guarantee is the key behavioral disclosure.
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 tight sentences with no wasted words. The key facts—dry-run, what it shows, no credit spending, and the mandatory call-first instruction—are all front-loaded and easy to parse.
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 single-parameter tool with no output schema, the description is complete: it explains the purpose, the safety profile (no credits), and the required workflow step. It tells the agent what the tool returns at a high level (what would be bought and the cost), which is sufficient for an agent to decide and communicate the result to a human.
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 already fully documents the single parameter, including the important clarification 'Set id (UUID), not the slug.' The description adds no additional parameter-level meaning, so the baseline score of 3 applies given 100% schema coverage.
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 clearly identifies the action (dry-run of purchasing) and the resource (audience set), and explicitly states what the preview shows: what would be bought and the cost. The phrase 'WITHOUT spending credits' and the title '(dry-run)' distinguish it from the real purchase operation buy_audience_set.
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 description gives explicit usage guidance: 'ALWAYS call this first and show the cost to the human.' This clearly tells the agent when to invoke the tool, though it does not explicitly name the alternative buy_audience_set for the actual purchase step. The context and sibling list make that alternative inferable, but not stated.
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.