Skip to main content
Glama
Hermoso

Hermoso

Official

Find a place to tag on Instagram or Facebook

search_meta_places

Find taggable Facebook Pages or Instagram places by name, link, or ID, returning pageId, name, and address to confirm before tagging a post.

Instructions

Find a PLACE to tag on an Instagram or Facebook post: a shop, cafe, restaurant, venue or landmark. Give its name with the city ("Blue Bottle Coffee Oakland"), or paste its Facebook Page link, an Instagram place link (instagram.com/explore/locations/...) or its numeric id. A pasted link or id is read and comes back as that Page's taggable pageId with its name and address, or a plain reason it cannot be tagged. Returns a handful of matching Facebook Pages that have an address: pageId, name, address, category, link. Pass the chosen pageId as locationId (Instagram) or place (Facebook) on post_to_meta, or instagramLocationId on schedule_post. These are matches to CONFIRM with the user (check the name and address; a place tag is public), and Instagram checks the place when the post is made. Needs no connected account. Spends about 1 credit per Page it checks (a name search checks up to 5 Pages, so about 5 to 7 credits); a pasted Facebook Page link or numeric id is about 1 credit; an Instagram place link costs nothing.

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": {
      "query": "<query>"
    },
    "name": "search_meta_places"
  }
}

Input Schema

NameRequiredDescriptionDefault
nearNooptional city or area to narrow a name search, e.g. "Paris"
limitNohow many Pages to check on a name search, 1 to 8 (default 5); each is about 1 credit
queryYesthe place name with its city (e.g. "Blue Bottle Coffee Oakland"), or a Facebook Page link, an Instagram place link, or a numeric id
get_costNotrue: return the price only; nothing runs or bills
idempotency_keyNochosen once, resent unchanged on retries: the same key never buys twice
expected_creditsNothe get_cost price; refused unbilled if the live price differs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.532
    • addedInput schema / properties / expected_credits
      Added value: +{
      +  "description": "the get_cost price; refused unbilled if the live price differs",
      +  "type": "number"
      +}
    • addedInput schema / properties / get_cost
      Added value: +{
      +  "description": "true: return the price only; nothing runs or bills",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "chosen once, resent unchanged on retries: the same key never buys twice",
      +  "type": "string"
      +}
  2. Addedv0.1.465

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only flag readOnlyHint=false and openWorldHint=true, so the description carries real weight and delivers: cost model per lookup type (name search ~5-7 credits, pasted FB link/id ~1 credit, Instagram place link free), what happens with a pasted link ("is read and comes back as that Page's taggable pageId... or a plain reason it cannot be tagged"), and the deferred validation that Instagram performs at post time. That is behavior an agent cannot infer from annotations or schema.

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

Conciseness4/5

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

Purpose and accepted input forms are front-loaded, and nearly every clause carries new information (cost, downstream parameter names, confirmation requirement). The single dense paragraph makes the cost details and the confirmation caveat easy to skim past, which keeps it from a 5.

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

Completeness5/5

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

For a lookup tool with no output schema, the description enumerates the return shape, describes the failure mode ("a plain reason it cannot be tagged"), quantifies cost, and tells the agent what to do with the result. Nothing material is missing for correct invocation.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns above that by explaining the practical effect of the parameters (limit drives credit spend, city-in-name narrows a name search, link vs id vs name take different code paths with different costs). It does not restate get_cost or idempotency_key, but those are already fully documented in the schema.

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 ("Find a PLACE to tag on an Instagram or Facebook post") and enumerates the entity types it covers (shop, cafe, restaurant, venue, landmark). It also lists the returned fields (pageId, name, address, category, link), so an agent can tell it apart from generic search siblings without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit input forms (name + city, Facebook Page link, Instagram place link, numeric id) and routes the output downstream: "Pass the chosen pageId as locationId (Instagram) or place (Facebook) on post_to_meta, or instagramLocationId on schedule_post." It also states the prerequisite ("Needs no connected account") and the human-in-the-loop step (confirm name and address with the user before tagging).

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