Skip to main content
Glama
hermoso-ai

Hermoso

Official

YouTube bulk report (thumbnail CTR, cards, end screens)

youtube_bulk_report
Read-only

Obtain YouTube thumbnail impressions, CTR, and related bulk reports. Scheduling creates a job; data becomes available within 48 hours.

Instructions

THE ONLY PLACE YOUTUBE PUBLISHES THUMBNAIL IMPRESSIONS AND THUMBNAIL CTR. This is a different API from youtube_channel_report — YouTube’s bulk Reporting API — and for a product that generates thumbnails it is the number that says whether the thumbnail actually worked. Reports: thumbnails (impressions + CTR per video per day) · thumbnails_by_source (the same, split by traffic source, traffic source DETAIL, device and OS) · cards (per-card impressions, clicks and click rate by card_id) · end_screens (per end-screen element) · traffic_source (with the UNCAPPED traffic_source_detail — youtube_channel_report caps that at 25 rows) · basic. IT IS SCHEDULED, NOT ON-DEMAND, AND THIS IS THE ONE THING YOU MUST EXPLAIN TO THE USER: the first call SCHEDULES a job and returns NO DATA. YouTube then writes one CSV per 24-hour Pacific day — the first within 48 hours — plus a backfill of the 30 days before scheduling, and files expire after 60 days. It can NEVER answer about a period before the job existed, so "we have no thumbnail history yet" is a real and correct answer on day one. An unknown report name is refused with the list. Zero rows means missing data for that window, never zero impressions. Read-only, 0 credits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNohow many recent daily files to read (1–14, default 7)
sinceNoYYYY-MM-DD — only files whose data starts on or after this
untilNoYYYY-MM-DD — only files whose data starts before this
reportNodefault thumbnails
scheduleNofalse = do not create the job if it is missing; just report that none exists
Behavior5/5

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

Annotations only declare readOnlyHint, openWorldHint, and destructiveHint. The description goes far beyond, disclosing the scheduled vs on-demand nature, the 48-hour delay, 30-day backfill, 60-day expiration, and the interpretation of zero rows as missing data rather than zero impressions. This is rich behavioral context that annotations cannot convey.

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 lengthy but each sentence delivers essential information. The unique value proposition is front-loaded, followed by the critical scheduling caveat, report list, and data interpretation notes. While dense, it avoids redundancy and earns its length given the tool's complexity; a minor deduction for being unstructured all-caps emphasis that could be tightened.

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 tool with no output schema and a complex asynchronous behavior, the description fully covers invocation semantics, data availability, common misunderstandings (zero rows, history limits), and differentiation from a sibling. An agent can confidently call this tool and interpret results correctly based solely on the description.

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?

Schema descriptions cover all 5 parameters, but the description adds crucial semantics: the meaning of the 'schedule' boolean (whether to create the job), the behavior for unknown report names (refused with a list), and the data availability implications of days/since/until. It also explains the 'basic' report and the uncapped traffic_source_detail, which are not obvious from the schema alone.

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 a specific verb ('bulk report') and resource ('YouTube'), enumerates the report types, and explicitly contrasts it with youtube_channel_report as a different API. It also highlights its unique value proposition for thumbnail metrics, making it immediately distinguishable 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 explicitly explains when to use this tool vs the alternative (youtube_channel_report), the scheduling mechanism, and the critical caveat that results are not returned on first call. It tells the agent exactly what to expect and what to communicate to the user, leaving no guesswork about invocation.

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