photos-mcp

Photos Search

photos_search

Read-onlyIdempotent

Search a Google Photos library using Google's own search for people, places, things, text in images, and dates, including archived items, with filters for photos or videos and paged results.

Instructions

Search the library with Google Photos' own search (people, places, things, text in images, dates; archived items included). Returns items {id, url, type, taken_at, tz_known, filename, description, place, favourite, archived}, next_cursor, coverage and freshness. place is null here (Google's search response has none) unless details=true, which also adds lat, lon and camera.

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": "photos_search"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	Items per page (1-50)
`media`	No	Only photos, only videos, or all (default)	all
`query`	Yes	What you'd type into Google Photos search
`cursor`	No	next_cursor from the previous page
`details`	No	Also lat, lon and camera per item, and place where missing (limit up to 20; one more request)

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.11.3Oct 27, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), yet the description adds real behavioral context: archived items are included, place is null unless details=true, and details costs one extra request and caps the page at 20. That cost/limit disclosure is exactly the kind of behavior annotations cannot express.

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?

Two dense sentences, front-loaded with the core capability before the return shape and details caveat. Slight over-packing of return field names that are largely redundant given the output schema, but nothing is wasted or buried.

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?

With an output schema present, the field enumeration is redundant, but the description still supplies what the schema cannot: archived-item inclusion, the place-null-without-details caveat, and the extra-request/limit-20 tradeoff. An agent has enough to call this correctly; only explicit sibling routing is missing.

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, and the description still adds meaning beyond it: it explains that details also backfills place and adds lat/lon/camera with a limit of 20 and an extra request, and that place is otherwise null. It does not elaborate on query syntax or cursor paging semantics, keeping it short of a 5.

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 ('Search the library') and enumerates what the search understands (people, places, things, text in images, dates), which distinguishes it from list-style siblings like photos_list and photos_albums. An agent can immediately tell this is the semantic-query path rather than a metadata enumeration path.

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

Usage Guidelines3/5

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

Usage is implied by 'with Google Photos' own search' and the note that archived items are included, which hints at scope, but no sibling (photos_list, photos_get, photos_show) is named as an alternative and no when-not-to-use condition is given. Adequate but leaves routing to inference.

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

Deploy Server