Get ICP match scores for leads. Filter by minimum score to find top matches. Returns paginated array of { leadId, leadName, icpMatchScore, matchedFields } sorted by score descending. Use campaignstack_list_icps to find ICP IDs. High-scoring leads can be added to lists via campaignstack_add_leads_to_list.
| Name | Required | Description | Default |
|---|---|---|---|
| icpId | Yes | ||
| limit | No | ||
| cursor | No | ||
| minScore | No |
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 declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds value by disclosing the paginated response shape, the exact fields returned, and descending sort order, which are not available in structured metadata. No behavioral trait contradicts the annotations.
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?
Three sentences, each carrying distinct information: action, filtering, output format/order, and related tools. There is no repetition or filler.
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 read-only paginated list with no output schema, the description covers the return fields, ordering, pagination, minimum-score filtering, and prerequisite tool for the required parameter. It could mention that scores may need to be generated first via trigger_icp_scoring, but this is not essential to invoking the operation correctly.
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?
With 0% schema description coverage, the description compensates partially: it maps minScore to the filtering concept, implies limit/cursor through pagination, and directs the agent to list_icps for icpId. It does not explain cursor semantics, limit bounds, or the default value, relying on the schema for those numeric constraints.
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 ('Get') and resource ('ICP match scores for leads'), states the output shape and ordering, and references the related list_icps tool for obtaining ICP IDs. This distinguishes it from nearby siblings like get_lead_score_breakdown and trigger_icp_scoring by focusing on the match-score read operation.
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?
It embeds workflow context by telling the agent to use campaignstack_list_icps to find ICP IDs and campaignstack_add_leads_to_list for high-scoring leads. It does not explicitly state when not to use it or compare it with alternatives, but the intended context is clear.
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.
The set is enormous and generally well-differentiated through detailed cross-referenced descriptions, but several clusters blur together: archive/delete/remove have inconsistent permanence semantics (delete_campaign vs remove_signal_watch vs archive_campaign), create_connection_watch_agent explicitly overlaps with set_account_watcher, and the parallel draft-checkup and playbook-proposal flows (run_draft_checkup/get_draft_checkup/accept_draft_checkup vs propose_playbook_change/get_playbook_proposal/decide_playbook_proposal) present near-identical decision pipelines.
Nearly every tool follows the campaignstack_<verb>_<noun> convention with disciplined get/list pairing and consistent verb choices (create/update/delete/pause/resume). Minor deviations like campaignstack_priority_enrich (adverb+verb) and campaignstack_whoami break the strict verb_noun pattern but are isolated and do not hinder navigation.
223 tools is an extreme surface for any MCP server. Even though each tool maps to a distinct API operation and the underlying platform is broad, the scale far exceeds the 50+ threshold for an extreme mismatch and will overwhelm agents with selection overhead.
The surface is exhaustive for the LinkedIn outreach domain: full campaign/workflow/lead-list lifecycles, ICP and persona management, content scheduling and approvals, inbox and messaging, enrichment and integrations, signal watches and exclusions, review queues, playbook versioning, workspace admin, billing, and notifications. Minor gaps like a missing delete_lead or delete_company are explained by shared-data semantics, so no critical dead ends remain.
