Skip to main content
Glama

Search

get_pinterest_search
Read-onlyIdempotent

Searches Pinterest for pins matching a keyword and returns pins plus a cursor to page. Each pin carries id, url, title, description, grid_title, created_at, images in five sizes (170x, 236x, 474x, 736x, orig), link, domain, board (name, url, pin_count) and pinner (username). Measured at about 110 KB for 17 pins; trim=true cuts that to 28 KB and keeps six fields per pin — id, url, description, created_at, images and pinner — dropping title, link, board and domain, so only skip trim when you need those. The board.url on each result feeds get_pinterest_board; for one pin's engagement counts use get_pinterest_pin.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
trimNoSet to true for a trimmed down version of the response
queryYesSearch query
cursorNoCursor

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / cursor / example
      Added value: +"Y2JVSG81V2sxcmNHRlpWM1J..."
    • addedInput schema / properties / query / example
      Added value: +"Italian Pot Roast"
    • addedInput schema / properties / trim / example
      Added value: +"false"
  2. First observed

TDQS

A5/5.0
Behavior5/5

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

Beyond the readOnlyHint and idempotentHint annotations, the description reveals concrete behavioral details: approximate response size for 17 pins, the 28 KB trimmed size, exactly which fields trim retains and drops, and the fact that results include a paging cursor. This is additive and highly useful context.

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?

The description is dense but every sentence earns its place: a clear one-sentence purpose, a compact field enumeration, measurable size guidance, and sibling routing. It front-loads the core behavior before diving into payload details.

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 search tool with pagination, an optional trim mode, and a rich output shape, the description covers all essential operational context: result contents, size implications, field trade-offs, cursor usage, and related endpoints. The presence of an output schema further reduces any missing return-value ambiguity.

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?

Although the schema already documents all three parameters, the description adds meaning beyond the schema: trim's field-level impact, the cursor's role in pagination, and the keyword matching behavior. It also clarifies the response shape per pin, making parameter choices more informed.

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 opens with a specific verb and resource: 'Searches Pinterest for pins matching a keyword and returns pins plus a cursor to page.' It clearly distinguishes the tool from sibling Pinterest tools by stating it is keyword-based and explicitly routes follow-ups to get_pinterest_board and get_pinterest_pin.

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 decision guidance: use trim only when full fields are needed, feed board.url to get_pinterest_board, and use get_pinterest_pin for engagement counts on a single pin. This tells an agent exactly when this tool and its alternatives are appropriate.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources