Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Get a saved query's numbers

saved_queries_stats_get
Read-onlyIdempotent

Retrieve aggregate statistics for a saved social media query over a 1–90 day UTC window, including daily posts by platform, top accounts and sites, sentiment, and insight counts.

Instructions

A saved query's numbers over the last days UTC days (default 30, up to 90): posts per day and platform by when they were posted, with zeros for quiet days; each platform's posts found in the window; the 10 accounts and linked sites heard from most; and posts by sentiment and by insights (not about the topic, needing a reply, risks, kinds, and yes answers to the query's own questions). Each count is of posts and of stories, where a repost or near-copy (duplicateOf) is a post but not a new story. Free: reads what earlier runs stored.

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": {
      "id": "<id>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "saved_queries_stats_get"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe saved query's id.
nowNoThe window's last day is this time's UTC day, ISO 8601. Default: now. Send the same value to read the same window again.
daysNoUTC days to count, today (the day of `now`) included, from 1 to 90. Default 30.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds worthwhile context beyond them: the call is free, it reads stored data from prior runs (implying results can be stale until a run happens), quiet days are zero-filled, and reposts count as posts but not as stories via duplicateOf. It does not state staleness limits or whether a run must exist first, which keeps it below a 5.

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

Conciseness5/5

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

A single dense but well-ordered sentence: window first, then each returned measure, then the counting rule, then the cost note. Every clause describes an actual output dimension; nothing is padding, and the free/stored-data caveat is placed last where it reads as a closing qualifier.

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

Completeness4/5

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

With no output schema and six parameters, the description carries the burden of describing return values and does so by enumerating each result group. What is missing is the shape of those results (nesting, field names, truncation beyond 'top 10'), so an agent knows the content but not the exact structure.

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 description coverage is 100%, so the schema already documents all six parameters, including the `days` default and 90-day cap that the description restates. The description adds modest semantic value by explaining that the window includes today, that quiet days appear as zeros, and by clarifying what the counts mean. Baseline 3 is appropriate.

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 states a specific resource and operation: aggregate statistics for one saved query over a bounded window. It enumerates the concrete measures returned (posts per day, platforms, top accounts, sentiment, insights), so an agent knows exactly what it gets. It does not explicitly contrast itself with saved_queries_run or saved_queries_stats_compare, leaving differentiation 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 context is implied rather than stated: 'Free: reads what earlier runs stored' tells the agent this is a read of previously computed data, so it should not be used to collect fresh posts. However, there is no explicit when-to-use/when-not guidance and no named alternative (e.g., use saved_queries_run to refresh, stats_compare to diff windows).

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

Deploy Server

Other Tools