Skip to main content
Glama
hermoso-ai

Hermoso

Official

Find Pinterest ad targeting options

search_pinterest_ads_targeting
Read-only

Identify valid Pinterest ad targeting IDs by type—INTEREST, GEO, LOCATION, AGE_BUCKET, KEYWORD and more—and drill into interest subtrees to ensure campaigns reach the intended audience.

Instructions

THE IDS AN AD GROUP’S targetingSpec NEEDS. create_pinterest_ads_campaign and create_pinterest_ads_ad_group accept interests, locales, locations, age buckets and keywords — this is where those values come from, and guessing one is the worst option available: Pinterest ACCEPTS a well-formed but wrong interest id and the campaign then quietly targets the wrong people. Pass targetingType (INTEREST, GEO, LOCATION, LOCALE, AGE_BUCKET, GENDER, APPTYPE, KEYWORD, AUDIENCE_INCLUDE, AUDIENCE_EXCLUDE) and optionally query to narrow the list. INTERESTS ARE A TREE: pass interestId instead to drill into one and get its children, which is how you get from "Food" to something specific enough to target. Pinterest publishes no search parameter of its own, so query filters the full list HERE — the note says so, because a filter we applied is not a filter the vendor applied. Read-only, 0 credits, no new permission (it uses ads:read, already granted).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo1–500, default 100
queryNonarrow the list to options mentioning this text (filtered here, not by Pinterest)
interestIdNodrill INTO one interest and return its child interests — how you walk the interest tree
adAccountIdNo
targetingTypeNowhich catalog to list — required unless you pass interestId
Behavior5/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false. The description adds value beyond annotations: it states 'Read-only, 0 credits, no new permission (it uses ads:read, already granted)' which covers cost and permissions not in annotations. It also discloses behavioral traits: Pinterest accepts wrong IDs silently, the query filter is local, and interest tree traversal. No contradictions 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.

Conciseness4/5

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

The description is moderately long (about 100 words) but every sentence provides substantive value: purpose, usage, tree navigation, query caveat, and safety. It is front-loaded with the main purpose and then details. Slightly verbose but well-structured and not padded; earns a 4 rather than 5 due to some redundancy (e.g., re-emphasizing read-only, already in annotations).

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?

For a tool with 5 parameters, an enum, and no output schema, the description covers most critical aspects: parameter usage, tree navigation, query semantics, and safety. However, it omits any guidance on adAccountId (which is likely required for scoping) and does not describe the response structure or pagination. These are gaps, but given the high schema coverage and the detailed narrative, it is nearly complete.

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 description coverage is 80%, so the baseline is 3. The description adds significant semantics for targetingType (lists enum values and explains catalog selection) and interestId (tree drill-down behavior). It clarifies query's local filtering. However, it does not explain adAccountId, which has no schema description either, leaving a small gap. Overall, it compensates well for the uncovered parameters.

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 states the specific verb 'search' and the resource 'Pinterest ad targeting options', and explicitly defines its purpose: supplying IDs for an ad group's targetingSpec used by create_pinterest_ads_campaign and create_pinterest_ads_ad_group. It clearly distinguishes itself from those creation tools and explains why accurate IDs are critical. This fully differentiates it from siblings.

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?

The description provides explicit usage context: 'this is where those values come from' and warns against guessing ('guessing one is the worst option available'). It explains when to use targetingType vs. interestId, how to narrow with query, and the tree-walking pattern. It also notes the query is a local filter (not Pinterest's), preventing misuse. This is comprehensive guidance for when and how to use the tool.

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