Skip to main content
Glama

Palimpsest — censorship, China economy and model-eval observatory

by io.github.beepboop2025
OverviewDiscussionsAdmin

One signal's full reading

get_signal
Read-onlyIdempotent

Read one named signal. Permitted signals return their bounded latest payload; China-economic signals in the denied lineage closure return explicit restricted/unavailable rights metadata and no values. Call list_signals first to discover valid names. Use this for the AI-model-evaluation side too: 'eval-registry' returns the pre-registered, hash-chained eval ledger with its verified flag and Merkle root, 'gfi-transcripts' returns a bounded view of the complete GFI v2 response matrix, and 'refusal-drift' returns the current frontier-model refusal reading on the frozen benign probe set; read 'eval-assurance' before turning either into a validity claim, and 'eval-journal' for the evidence-bound explanation and source receipts, or 'eval-findings' for the current deterministic article edition. Distinct from gfw_reading, which merges the two Great Firewall layers into one combined view.

Input Schema

NameRequiredDescriptionDefault
nameYessignal name from list_signals, e.g. 'ooni-gfw', 'eval-registry', 'eval-assurance', 'eval-journal', 'eval-findings', 'gfi-transcripts' or 'refusal-drift'
max_rowsNocap on long row arrays (dataset, ranked, samples). Default 25 keeps a call small enough not to stall a tool loop; the generative-firewall-index dataset is 132 rows. Any cap applied is reported in the response with the true total, never silently.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / name / description
      Previous value: -"signal name from list_signals, e.g. 'ooni-gfw', 'eval-registry' or 'refusal-drift'"New value: +"signal name from list_signals, e.g. 'ooni-gfw', 'eval-registry', 'eval-assurance', 'eval-journal', 'eval-findings', 'gfi-transcripts' or 'refusal-drift'"
  2. Changed1 schema field changed
    • addedInput schema / properties / max_rows
      Added value: +{
+  "default": 25,
+  "description": "cap on long row arrays (dataset, ranked, samples). Default 25 keeps a call small enough not to stall a tool loop; the generative-firewall-index dataset is 132 rows. Any cap applied is reported in the response with the true total, never silently.",
+  "maximum": 500,
+  "minimum": 1,
+  "type": "integer"
+}
  3. Changed1 schema field changed
    • changedInput schema / properties / name / description
      Previous value: -"signal name from list_signals, e.g. 'ooni-gfw' or 'generative-firewall-index'"New value: +"signal name from list_signals, e.g. 'ooni-gfw', 'eval-registry' or 'refusal-drift'"
  4. Changed1 schema field changed
    • changedInput schema / properties / name / description
      Previous value: -"e.g. 'ooni-gfw'"New value: +"signal name from list_signals, e.g. 'ooni-gfw' or 'generative-firewall-index'"
  5. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the description rightly focuses on what annotations cannot convey: denied-lineage signals return restricted/unavailable rights metadata with no values, and row caps are reported with the true total rather than applied silently. It stops short of describing invalid-name errors or response shape, keeping it below a 5.

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 opening sentence is front-loaded and the rest is routing information rather than filler, but the description is dense and runs long for a two-parameter read tool. Most sentences earn their place, though the eval-side enumeration is heavy.

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 no output schema, the description does useful work describing return values: bounded latest payloads, restricted rights metadata, the eval ledger's verified flag and Merkle root, and a bounded GFI matrix view. It leaves out error behavior for unknown names, which keeps it from a 5.

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. The description adds real semantic value by explaining what the signal names mean in context ('eval-registry' returns the hash-chained eval ledger, 'gfi-transcripts' the bounded GFI matrix, 'refusal-drift' the current refusal reading) and by tying max_rows to non-silent truncation.

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 ('Read one named signal') and immediately distinguishes itself from gfw_reading and list_signals. It explains what permitted versus restricted signals return, so the agent knows exactly what this tool yields.

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 says to call list_signals first for valid names, names the eval-side entries and their intended use, and tells the agent to read eval-assurance before making validity claims and eval-journal/eval-findings for supporting evidence. It also names gfw_reading as the alternative for merged firewall views.

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
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources