Generate a personalized LinkedIn first message using full campaign context. Fetches lead profile, campaign goal, ICP, and persona data from Convex, then uses AI to craft a tailored message. Use only for first messages (no prior conversation). For follow-ups with conversation history, use campaignstack_craft_followup instead.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by revealing that it fetches lead profile, campaign goal, ICP, and persona data from Convex and then uses AI to craft the message. It could go further by explicitly stating that it only returns a draft and does not send the message, but this is not a contradiction and the readOnly hint mitigates the gap.
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?
Two sentences, no filler. The main purpose is front-loaded, followed immediately by usage constraints and the alternative tool. Every sentence earns 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 zero-parameter generation tool, this is largely complete: it describes the inputs it fetches, the output it produces, and when it should not be used. The only minor gaps are that it does not explicitly state how the target lead/campaign is resolved (since there are no parameters) and does not state the return format, but the readOnlyHint and 'craft a message' wording make these low-risk omissions.
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 tool has zero parameters, so there is no parameter documentation burden on the description. The description still adds meaning by listing the contextual data sources (lead profile, campaign goal, ICP, persona) that shape the generated message, which helps the agent understand what information influences the output.
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 states a specific verb ('Generate'), a clear resource ('personalized LinkedIn first message'), and the context used ('full campaign context'). It also names the exact sibling alternative, campaignstack_craft_followup, so the tool is easy to distinguish from nearby craft 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?
Explicitly says 'Use only for first messages (no prior conversation)' and routes follow-ups to campaignstack_craft_followup. This gives the agent a clear decision rule for when to select this tool versus its sibling.
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.
Many tools share the same verb prefix (create_, list_, update_, get_) across closely related resources, so pairs like add_lead_to_external_list vs add_lead_to_sequence, create_signal_agent vs create_signal_watch, and approve_review vs approve_content_post can be confused. The descriptions are unusually detailed and cross-referenced, which mitigates but does not eliminate the ambiguity inherent in a 282-tool surface.
Virtually every tool follows the campaignstack_verb_noun snake_case pattern, which is highly predictable. Minor deviations exist: destructive operations mix remove_ and delete_ (remove_lead_list vs delete_campaign), AI generation uses both craft_ and generate_, and the seo_/search_console_ subdomains introduce a second prefix convention.
282 tools is an extreme mismatch by any reasonable standard, exceeding the 50+ threshold by more than 5x. Even for a full B2B outreach platform, this surface is far too large and would be better consolidated into higher-level operations or grouped sub-servers.
The tool surface is impressively comprehensive, covering campaigns, workflows, leads, content, ads, SEO, integrations, billing, and more with CRUD-level depth. Minor gaps remain: no single-ICP getter, no direct pause/delete for search watches, and no explicit delete for ad campaigns (only archive via update).
