Skip to main content
Glama

Pupul data export guides

by com.noctaracorp

Find the file holding a platform’s conclusions about you

get_inference_file
Read-only

Which file inside a platform’s data export holds the platform’s own conclusions about the person: not what they did, but what it decided they are. Returns the exact filename, the request tier that actually ships it (several platforms hide it behind a bigger or separate request), what it holds, and the trap for that platform. Covers 11 platforms: spotify, linkedin, x, tiktok, instagram, amazon, google, chatgpt, claude, netflix, grok. Some answer view-only or none-found, and the tool says so rather than inventing a filename. This describes where a person’s own data lives; it never reads it and never reports what any platform concluded about anyone.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
platformYesWhich platform. Common spellings and aliases resolve: twitter, meta, google takeout, youtube.

TDQS

A4.4/5.0
Behavior5/5

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

The description goes well beyond the readOnlyHint annotation by disclosing that some platforms return view-only or none-found results, that the tool will not invent a filename, and that several platforms hide the file behind a larger or separate request. This gives the agent realistic expectations about edge cases and limits.

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 dense but efficient, front-loading the core question and then listing concrete return values and platform coverage. A few clauses could be tightened, but every sentence contributes useful information.

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?

With no output schema, the description appropriately explains what the tool returns, including edge cases (view-only, none-found) and the 'trap' detail. It also declares the closed set of supported platforms, which matches openWorldHint=false and leaves no critical ambiguity for an agent calling the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already fully documents the platform parameter, including alias resolution, so the schema carries the load. The description adds the supported platform list, which is useful context, but does not need to explain parameter syntax further.

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 is precise: it finds the file in a data export that holds a platform's conclusions about a person, not their raw activity. It states exactly what is returned (filename, request tier, contents, trap) and names the 11 platforms covered, making the tool's function unmistakable.

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

Usage Guidelines4/5

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

The description clearly implies when to use the tool: when locating the conclusions file inside a platform export, and it clarifies what the tool does not do (it never reads the data or reports conclusions). It does not explicitly name sibling alternatives or exclusion conditions, but the context is strong enough for an agent to select it correctly.

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

All Pupul data export guides toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation4/5

Each get_* tool targets a distinct deliverable—viewer links, export steps, inference file, wait times, or product facts—and the aggregate how_to_see_what_a_platform_knows explicitly positions itself as the router for whole-platform questions. The only mild overlap is that get_export_guide and get_wait_times both mention wait times, but their primary outputs are clearly different.

Naming Consistency4/5

Seven tools follow a clean get_<object> pattern, making the target of each call predictable. how_to_see_what_a_platform_knows breaks the pattern as a sentence-style name, but it is a deliberate aggregate entry point rather than a sign of inconsistency.

Tool Count5/5

Eight tools is a well-scoped set for an informational guide server: individual getters for specific facts, plus one combined entry point. No tool feels redundant or purely decorative.

Completeness5/5

The server covers the full question flow around data exports—request steps, wait times, inference files, and a local viewer—across the listed platforms, and adds LUX/Pupul factual tools for adjacent product questions. There are no obvious dead ends; the aggregate tool routes to individual tools where needed.

Resources