Skip to main content
Glama

Palimpsest — censorship, China economy and model-eval observatory

by io.github.beepboop2025

List published signals

list_signals
Read-onlyIdempotent

List every published signal Palimpsest exposes across its three applications: name, one-line description and source URL for each. Censorship and information control — OONI Great Firewall probes, Censored Planet, IODA outages, circumvention demand, takedown and redaction pressure, and the board's own verdict. China economics — explicit metadata-only rights status for affected observations, pulse, forecast and derivative surfaces; no denied values are returned. AI model evaluation — the tamper-evident, pre-registered eval registry (hash-chained and Merkle-rooted), its claim-by-claim assurance ceiling, evidence-bound Eval Journal, deterministic live findings, and frontier-model refusal drift, alongside the Generative Firewall Index over a named China-focused panel. Takes no arguments. Call this first to discover signal names, then get_signal for one full reading.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description adds meaningful output behavior: the exact fields (name, one-line description, source URL) and the guarantee that 'no denied values are returned.' It does not contradict annotations and enhances the agent's expectation of what the tool returns.

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 longer than a simple listing, but each section (the three application categories) provides essential context for an agent to decide to call it. It is front-loaded with the purpose and ends with usage guidance. While somewhat verbose, the information density justifies the length.

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?

Given that the tool has no parameters and no output schema, the description fully covers what an agent needs: what it returns, the categories of signals, and the recommended next step (get_signal). Nothing is missing for correct invocation.

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 input schema has zero parameters, which is fully covered by the schema itself (100% coverage). Per the rubric, the baseline is 4 for no parameters. The description's note that it 'takes no arguments' reinforces but does not add beyond what the schema already makes obvious.

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 uses a specific verb ('List') and resource ('published signals') and details the exact content (name, one-line description, source URL) across three named applications. It clearly distinguishes itself from the sibling get_signal by stating it returns summaries, not full readings.

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?

Explicitly states 'Call this first to discover signal names, then get_signal for one full reading,' providing both when-to-use and the preferred follow-up tool. This is unambiguous guidance for an agent.

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

All Palimpsest — censorship, China economy and model-eval observatory 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

A4.2/5.0
Disambiguation3/5

get_newsroom 和 get_signal 之间的边界不够清晰，尤其是 economy 视图与中国经济信号、machine-analysis 视图与 eval 信号在功能上有所重叠；query_economic_observations 也与中国经济读取工具有部分交叠。不过每个工具的详细描述都试图说明其特定用途，且 gfw_reading、whats_happening 与 get_signal 的差异已被明确点出，因此并非完全无法区分。

Naming Consistency3/5

大多数工具遵循动词_名词模式（get_newsroom, get_signal, list_signals, query_economic_observations），但 gfw_reading 是名词+动名词结构，whats_happening 是口语化问句，打破了统一模式。整体仍保持小写蛇形且可读，属于混合惯例但可接受的级别。

Tool Count5/5

6 个工具对于一个横跨审查、中国经济和 AI 模型评估三个应用的观察站来说非常合适：既有足够的功能入口，又不过度碎片化。每个工具都对应一个明确的职责面，且内部承载多个信号/视图，工具数量与领域复杂度匹配良好。

Completeness4/5

工具覆盖了信号发现（list_signals）、单信号读取（get_signal）、组合视图（gfw_reading）、跨信号判断（whats_happening）、报道/编辑表面（get_newsroom）以及经济权限状态（query_economic_observations），基本没有明显死路。次要缺口如缺少中国经济非受限数据的直接读取或信号历史访问，但这些受制于设计策略或可通过现有工具间接获得。

Resources