top_message_correspondentsThe people the user has exchanged the most LinkedIn messages with, most-messaged first, with how many messages and when they last spoke. Use for 'who have I exchanged the most messages with?', 'who do I talk to most on LinkedIn?', and similar.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many people to return (max 50). |
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=true, and the description adds meaningful behavioral detail: results are sorted most-messaged first, and each result includes message count and last-interaction time. It does not discuss caveats like whether counts include both sent and received messages, but the disclosed behavior is sufficient for this simple read operation.
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 concise sentences with no filler. The first sentence states exactly what is returned and in what order; the second provides concrete example queries that help an agent recognize when to invoke it.
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 simple, read-only tool with one optional parameter and no output schema, the description is complete enough: it specifies the result content, ordering, and likely invocation triggers. There is no hidden behavior an agent would need to discover elsewhere.
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 coverage is 100%, so the only parameter (limit) is already documented with its maximum value. The description does not need to add much, but it also doesn't mention how limit behaves when omitted, which would have been a small bonus.
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 resource (LinkedIn message correspondents), the metric (most messages exchanged), ordering, and the fields returned. It reads as a specific query tool and is easily distinguished from siblings like get_messages_summary or search_connections.
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 explicitly maps the tool to natural-language use cases like 'who have I exchanged the most messages with?' and 'who do I talk to most on LinkedIn?'. It does not name alternatives or exclusions, but the usage context is clear enough for an agent to select it appropriately.
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.
Each tool targets a distinct resource and action, with clear boundaries even within overlapping domains like LinkedIn (search vs. free-form query vs. profile vs. summary) and graph deletion (soft single, bulk soft, permanent single). Descriptions explicitly cross-reference related tools to prevent misselection.
The vast majority follow a consistent verb_noun pattern (get_, list_, search_, create_, delete_, etc.). A few noun-phrase exceptions like linkedin_analytics, mutual_connections, similar_objects, and what_needs_attention deviate slightly, but they are still descriptive and do not create confusion.
At 66 tools this is far beyond the 25+ threshold considered too many, even though the server covers many integration domains. Each domain has a coherent subset, but the overall surface is heavy for agents to navigate and would benefit from consolidation or namespacing.
The set provides deep read/search coverage across Gmail, Slack, Calendar, LinkedIn, HubSpot, Obsidian, Twitter, and a graph store, with core write operations for calendar, drafts, Slack, and graph objects. Minor gaps exist—notably no calendar delete, no direct Gmail send to third parties (only drafts), and no LinkedIn post/message actions—but these appear deliberate and do not block typical workflows.