Skip to main content
Glama
Sign In
photos-mcp

photos-mcp

by benjamin-di
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Photos Canary

photos_canary
Read-onlyIdempotent

Checks whether agents can access a Google Photos library page and its thumbnail, caching the health verdict to monitor photo search and viewing availability.

Instructions

Monitoring: one real check of the path agents use (a library page of 1 item and its thumbnail); the verdict is cached 55 min (transient failures: 5 min) and calls in between return it (cached: true). {ok, code, checked_at, cached, snapshot_age_s, generation}; ok is false on any error code, or with code snapshot_stale when the snapshot is older than 3 h or dated in the future. Never fails.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "photos_canary"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.3

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial context on top: cache lifetime (55 min, 5 min on transient failures), the exact return shape, the rule that ok is false on any error code or on snapshot_stale (>3 h or future-dated), and the key guarantee 'Never fails'. That is precisely the behavioral detail an agent needs to interpret the result without misreading a stale verdict as a live one.

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?

Front-loaded with the 'Monitoring:' framing and compact overall, with every clause carrying real information (cache TTLs, field list, staleness rule). The semicolon-chained final sentence is dense and slightly run-on, but no sentence is wasted.

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?

Though an output schema exists, the description still explains the verdict fields and, more importantly, the staleness thresholds and 'Never fails' behavior that an agent needs to act on the result correctly. For a zero-param monitoring tool, nothing material 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. Nothing in the description contradicts or misuses the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — 'one real check of the path agents use (a library page of 1 item and its thumbnail)' — and frames it as 'Monitoring', which separates it from the read/write photo siblings. It does not explicitly say 'this is the health check, not a photo fetch', but the content makes the distinct role apparent.

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?

The 55-minute cache and 5-minute transient-failure cache imply that repeated calls are cheap and that the tool is meant for periodic health verification, but the description never states when to call it (e.g., on suspected API errors) or when not to. Usage must be inferred from the caching semantics rather than read explicitly.

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