Skip to main content
Glama

Read insights

get_insights
Read-onlyIdempotent

The member's dashboard, stats, time-away summary, analytics, LinkedIn suggestions, and their LinkedIn connection, views and queued changes. Actions: dashboard, stats, away, analytics, analytics_home, analytics_search, analytics_selection, analytics_chat, linkedin_text, linkedin_account. Call with action "help" for each action's fields.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "get_insights"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
paramsNoFields for the action. Call with action "help" to list each action's fields.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "dashboard",
      -  "stats",
      -  "away",
      -  "analytics",
      -  "analytics_home",
      -  "analytics_search",
      -  "analytics_selection",
      -  "analytics_chat",
      -  "linkedin_text",
      -  "help"
      -]New value: +[
      +  "dashboard",
      +  "stats",
      +  "away",
      +  "analytics",
      +  "analytics_home",
      +  "analytics_search",
      +  "analytics_selection",
      +  "analytics_chat",
      +  "linkedin_text",
      +  "linkedin_account",
      +  "help"
      +]
  2. Added

TDQS

B3.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds two behavioral facts not in the annotations: that the data is scoped to 'the member' and that a help action exists for schema discovery. It says nothing about return shape, pagination, or whether any action is expensive, which is the remaining gap for a 10-action multiplexer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and the content enumeration is front-loaded, but the first sentence's domain list and the second sentence's action list substantially overlap, so the same information is effectively presented twice. The closing 'help' sentence duplicates the schema text verbatim, which is wasted space in a two-sentence description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, ten distinct read actions, and a nested free-form params object, the description carries a heavy load; deferring field semantics to a runtime 'help' call is a legitimate strategy but means the agent cannot plan a call without an extra round trip. It is complete enough to know what the tool is for and how to begin, but incomplete for choosing among the closely related analytics actions or anticipating return content.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: the free-form 'params' object is described, but the action enum is undocumented in the schema. The description partially compensates by mapping domains to action groups (e.g. 'away' → time-away summary, 'linkedin_text' → suggestions, 'linkedin_account' → connection, views, queued changes) and by pointing to action "help" for per-action fields. Still, 'analytics' vs 'analytics_home' vs 'analytics_search' vs 'analytics_selection' vs 'analytics_chat' are listed with zero disambiguation, leaving the riskiest part of a 11-value enum unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the concrete data domains the tool exposes (dashboard, stats, time-away, analytics, LinkedIn text/account) and enumerates the exact action set, so an agent can tell this is the read-side insights aggregator. It does not, however, differentiate itself from look-alike siblings such as get_profile, get_account, or get_analytics-adjacent tools, so the boundary is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the domain listing and the action enum; there is no statement of when to pick this over get_profile/get_account, and no exclusions. The one explicit procedural guideline is 'Call with action "help" for each action's fields', which is genuinely useful but is about parameter discovery rather than tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.