Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Write a query from a description

query_suggest_post
Read-onlyIdempotent

Write or refine a Boolean social media query from a plain-language monitoring brief, test it against example posts, and preview validation before searching.

Instructions

Write a Boolean query from a plain-language description of what to monitor, optionally with example posts it should and shouldn't find, or refine an existing query. The query is written by AI, then read, explained and planned like validate, and run over the example posts. Show it to the user before searching with it. Free.

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": {
      "brief": "<brief>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "query_suggest_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
briefYesWhat to monitor, in plain words and any language: brands, people, topics, places, what to leave out. With `previousQuery`, the change to make to that query, such as `also exclude job ads`.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
examplesNoExample posts, to check the query against and to help write it.
explainInNoLanguage of the explanation, the note and the refusal: `en` (default) or `es`.
languagesNoLanguages the posts should be in, as two-letter ISO 639-1 codes. Any language when omitted.
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.
platformsNoPlatforms to plan for. Every platform when omitted.
maxCreditsNoCredits a search would be allowed, for the plan and its estimate. Default 100.
previousQueryNoA query in Social Fetch's syntax to refine as `brief` asks, instead of writing a new one.
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

A3.9/5.0
Behavior4/5

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

Adds substantive behavior beyond the annotations: the query is AI-generated, then validated/explained/planned, then exercised against the example posts, and the result must be surfaced to the user before any search. It also discloses cost ('Free'), which the readOnly/idempotent hints do not convey. It stops short of describing latency, refusal behavior, or what the response contains, which matters given there is no output schema.

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 purpose is front-loaded in the first clause, which is good, but the middle sentence ('then read, explained and planned like validate, and run over the example posts') is grammatically muddled and gestures at a sibling's behavior without explaining it. The 'Free.' fragment is useful but dangling at the end.

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?

For a 10-parameter, nested-object tool with no output schema, the description covers the pipeline and the user-confirmation rule but leaves the return shape and the conversation_id handshake (which the schema flags as critical and non-parallel) unexplained at the description level. An agent can call it, but must read the schema closely to do so correctly.

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 every parameter well. The description only echoes two of them semantically (brief and examples, via 'optionally with example posts it should and shouldn't find') and says nothing about llm_model, conversation_id, maxCredits, or the refine mode's use of previousQuery. Baseline 3 for full schema coverage.

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

Purpose5/5

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

States a specific verb and resource — writing a Boolean query from a plain-language brief — and explicitly covers the second mode, refining an existing query. It also names the downstream siblings it relates to (validate, search), so an agent can place it in the workflow without opening any schema.

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

Usage Guidelines4/5

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

Gives real routing context: it is a pre-search step ('Show it to the user before searching with it') and it is the candidate-generation counterpart to validation and search. It does not state an explicit when-not-to-use condition (e.g. jump straight to search or validate instead), so it falls short of a full 5.

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