Skip to main content
Glama

ainote

by io.github.seunghan91

judgment_submit

Request a human judgment (L3 layer) by attaching evidence — approval, evidence, or verdict. This is the ONLY door an agent has into the judgment queue.

🔴 decision is REJECTED with an error if passed — judgments are always created with decision='pending'. Only a human decides them (from the /command queue). Use judgment_list afterwards to check whether this judgment has since been decided.

risk_tier controls urgency: 1=destructive (blocks execution until decided), 2=reversible (may auto-proceed after a wait window), 3=informational (auto-expires after 24h).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYesapproval | evidence | verdict.
summaryYesOne sentence: what is being judged (required).
evidenceNoFree-form evidence attached to the request — links, numbers, diff summaries.
risk_tierNo1=destructive 2=reversible 3=informational. Default: 2.
project_idNoOptional project this judgment relates to.
subject_idNoOptional. UUID of the Assumption or Task this judgment is about.
subject_typeNoOptional. Pair with subject_id. Only Assumption or Task are allowed.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
  2. Added

TDQS

A4.9/5.0
Behavior5/5

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

Beyond annotations (which only say readOnly=false, destructive=false), the description reveals critical behaviors: decisions are always created as 'pending', only humans decide them, risk_tier controls urgency with specific consequences (blocks execution, auto-proceed after wait, auto-expire after 24h), and passing `decision` is rejected. This is rich behavioral context not present in annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured in three paragraphs, each serving a distinct purpose: (1) core function and uniqueness, (2) critical constraint and follow-up, (3) risk_tier semantics. It is front-loaded with the most essential information and contains no redundant or filler content; every sentence earns its place.

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 7 parameters, no output schema, and minimal annotations, the description provides comprehensive context: purpose, workflow, constraints (decision rejection), risk_tier behavior, and how to verify completion (judgment_list). It equips the agent to invoke the tool correctly and understand downstream effects, despite lacking explicit return-value details.

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 covers all 7 parameters (100% coverage), so baseline is 3. However, the description adds meaning beyond the schema by explaining the behavioral impact of `risk_tier` (1 blocks, 2 reversible, 3 auto-expires) and explicitly warning against a non-schema parameter `decision`. This supplementary guidance raises the score.

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 clearly states the tool's function: 'Request a human judgment (L3 layer) by attaching evidence — approval, evidence, or verdict.' It specifies the exact resource (human judgment queue) and action (request/submit), and distinguishes it as 'the ONLY door an agent has into the judgment queue' from siblings like judgment_list.

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?

It explicitly indicates when to use this tool (when human judgment is needed) and warns against passing `decision`, stating it is rejected with an error. It also directs to 'Use judgment_list afterwards' to check decision status, providing a clear alternative and follow-up workflow. This satisfies explicit when/when-not/alternative guidance.

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

All ainote 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

A3.5/5.0
Disambiguation4/5

Most tools clearly target distinct resources (tasks, docs, graph, sync, env_sync, handoffs, judgments, projects, vault). A few pairs could confuse, like sync_push vs vault_sync (which has a push action) and env_sync_write vs env_sync_txn_push, but descriptions mostly clarify boundaries.

Naming Consistency3/5

Names are predominantly snake_case with a noun_verb pattern (e.g., sync_push, task_write), but there are notable inconsistencies: plural/singular mismatches (dev_docs_read vs dev_doc_write, tasks_read vs task_write), verb-first names (list_papers, get_setup_guide, judgment_submit), and a dotted sub-namespace (env_sync.secret_pull) mixed with flat names (env_sync_txn_push).

Tool Count2/5

35 tools is a large surface for a personal note/sync server. While it spans many domains (auth, tasks, docs, sync, env_sync, graph, etc.), the sheer number feels heavy and likely overwhelms agents with too many choices, especially when several tools are consolidated sub-action surfaces.

Completeness3/5

Most domains have reasonable CRUD coverage (tasks, dev docs, graph, sync, env_sync, vault). However, noticeable gaps exist: memory has no write tool (only read), papers only support listing (no create/update/delete), assumptions have write but no dedicated read or delete, and judgment is effectively submit-and-list only.

Resources