Skip to main content
Glama
Sign In

EDNA — On-Device Human Sensing for AI

by space.openos
OverviewDiscussionsAdmin

edna.get_writing_process

Writing-process channel (production): HOW the current message came to be — typing bursts, thinking pauses (the reason is never inferred), correction runs, tempo dynamics and a quantized 12-step timeline. Never content, never key identity.

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": "edna.get_writing_process"
  }
}

Input Schema

NameRequiredDescriptionDefault
sessionNoTest session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the "default" session.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

No annotations exist, so the description carries the burden, and it does disclose meaningful behavioral traits: reasons for pauses are never inferred, and the channel never returns content or key identity — an important privacy/scope boundary an agent could otherwise violate by assuming. It still omits auth requirements, error/empty-session behavior, and whether data is per-message or per-session.

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?

One front-loaded sentence with the resource first, then the enumerated contents, then the negative scope clause; no filler. Slightly dense with jargon ('quantized 12-step timeline') that is left unexplained.

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?

No output schema exists, so the description must convey return shape, and it does list the payload components (bursts, pauses, corrections, tempo, timeline). For a single optional-param read tool this is nearly sufficient; interpretation of the 12-step timeline and units remain unstated.

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?

There is a single optional parameter and schema coverage is 100%, so the schema already documents the session id, its regex, header fallback, and default. The description adds nothing about session scoping or how the session interacts with the returned timeline.

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?

Names a specific resource ('Writing-process channel') and enumerates concrete outputs — typing bursts, thinking pauses, correction runs, tempo dynamics, a quantized 12-step timeline. The negative framing ('Never content, never key identity') also draws a boundary against content/identity siblings, though no sibling is named explicitly.

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 '(production)' tag and the 'HOW the current message came to be' framing imply the use case — retrieving process/timing metadata for a message rather than its text. However, there is no explicit when-to-use statement, no exclusions, and no named alternative among the many edna.get_* siblings.

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

All EDNA — On-Device Human Sensing for AI 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