Skip to main content
Glama
hermoso-ai

Hermoso

Official

Search a public Instagram hashtag

search_instagram_hashtag
Read-only

Fetch public Instagram posts by hashtag on your own Meta account, returning captions and engagement to analyze market language for competitor and category insights.

Instructions

Read the PUBLIC Instagram posts carrying a hashtag — the caption, the media, the permalink and the like and comment counts — on the brand’s own Meta credentials rather than a scraper. This is category and competitor listening: find how a market actually talks about a product, then USE it — feed the captions into mine_angles, or write the brand’s next post or ad from the language you found. TWO EDGES AND THEY ANSWER DIFFERENT QUESTIONS: edge:"recent" (default) is what has been posted in the LAST 24 HOURS, which is Meta’s own hard limit, so a hashtag with millions of posts legitimately returns ZERO on a quiet day — never report that as "nobody is posting about this", ask again with edge:"top", which has no time limit. Only PUBLIC, non-promoted posts are ever returned, from public accounts only, and never in chronological order. A SHORT RESULT IS NOT A SMALL HASHTAG: Instagram limits a page by total response SIZE rather than by post count, so a tag whose posts are carousels returns fewer rows per page than a tag whose posts are single images — never compare two tags by how many rows came back. BUDGET: Instagram allows each Instagram account 30 UNIQUE hashtags in any rolling 7 days, so choose the tags deliberately; re-querying one already used in the window is free. Read-only, 0 credits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagYesthe hashtag — "skincare", "#skincare" or an instagram.com/explore/tags/… link all work. Instagram matches it EXACTLY and tags carry no spaces or punctuation.
edgeNo"recent" (default) = posted in the last 24 hours; "top" = the best-performing posts, with no time limit. Use "top" whenever "recent" comes back empty.
limitNohow many posts (1–50, default 10). Instagram bounds a page by how much DATA it holds, not by how many posts, so a big ask is fetched in several smaller pages automatically and may still come back short on a carousel-heavy tag — a short result is NEVER a measure of the tag’s size.
pageIdNoFacebook Page id — omit when only one Page is connected. Its linked Instagram account is what Meta charges the hashtag budget against.
Behavior5/5

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

Annotations only declare safe/read-only/open-world hints, but the description adds critical behavioral context: uses brand Meta credentials (not scraper), only public non-promoted posts, no chronological order, results bounded by data size not post count, and per-account budget of 30 unique hashtags per rolling 7 days. No contradiction with annotations.

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?

Long but every sentence earns its place; no fluff. Purpose is front-loaded, edges separated, caveats (short result vs small tag) and budget explained in tight, scannable blocks. The use of caps for key warnings aids comprehension without losing brevity.

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?

Given the tool's complexity (Instagram quirks, budget, edge behavior), the description covers everything an agent needs to call it correctly and interpret results: return fields, edge semantics, data-size pagination caveat, budget limits, and the 'recent' empty result trap. No output schema needed since returned fields are stated.

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

Parameters5/5

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

Even though schema describes parameters 100%, the description enriches each: tag format examples and exact-match rule, edge semantics and when to switch, limit explanation about carousel-heavy pages returning fewer rows, and pageId's role in budget attribution. Goes well beyond schema descriptions.

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?

The description clearly states the tool reads public Instagram hashtag posts including caption, media, permalink, and counts, distinguishing it from generic search tools. It explicitly frames the use case (category/competitor listening) and differentiates itself from siblings by focusing on hashtags and Meta credentials.

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?

Provides explicit when-to-use scenarios (e.g., market listening, feeding captions into mine_angles) and when-not (avoid misinterpreting empty results). Clearly explains the edge:'recent' vs edge:'top' decision rule and the 'recent' 24-hour limit, plus budget considerations — all actionable guidance beyond the schema.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hermoso-ai/hermoso'

If you have feedback or need assistance with the MCP directory API, please join our Discord server