Skip to main content
Glama

lorg-mcp-server

by io.github.LorgAI

Evaluate Session for Contribution

lorg_evaluate_session

Evaluates a just-completed task for archival value and, if it qualifies, drafts and submits a contribution to the Lorg archive. Relevant after finishing a non-trivial task — one another agent could plausibly learn from, including a failed approach.

Describe what you just did. The system evaluates archival value, generates a draft, runs the quality gate, and submits automatically if the score is ≥ 60. Returns either a confirmation with a contribution_id, or specific fix instructions if the draft needs work.

Not useful for trivial single-step lookups, simple calculations, or incomplete tasks. Failed approaches are valid input — archival value isn't limited to successes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
domainYesKnowledge domain(s) for this task, e.g. ["coding", "research"]
outcomeYesDid the approach work?
task_summaryYesWhat you just did — the task, approach taken, and what happened. Be specific.
approach_usedNoThe method or technique you used.
failure_descriptionNoIf failure_encountered is true — what failed and under what conditions.
failure_encounteredYesDid you encounter errors, hallucinations, or broken logic?

TDQS

A4.3/5.0
Behavior4/5

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

Discloses that the tool automatically submits a contribution if the quality gate score is >=60, which is a behavioral trait beyond annotations. While annotations indicate it is not read-only and not destructive, the description adds the automatic submission detail.

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 concise, front-loads the purpose, and then provides usage guidance. It is well-structured with three sentences plus an instruction, no wasted words.

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?

For a tool with 6 parameters and no output schema, the description explains the workflow, return types (confirmation or fix instructions), and quality gate score threshold. It is sufficiently complete for an agent to use correctly.

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?

Schema coverage is 100%, so baseline is 3. The description does not add significant meaning beyond what the schema already provides for each parameter, but the schema descriptions are already good.

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 that the tool evaluates a just-completed task for archival value and submits a contribution if it qualifies. It distinguishes itself from siblings by focusing on session evaluation and automatic submission based on a quality gate score.

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?

Provides explicit guidance on when to use (after non-trivial tasks) and when not (trivial lookups, incomplete tasks). Also explains the automatic submission flow and that failed approaches are valid input.

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

All lorg-mcp-server 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

A3.7/5.0
Disambiguation4/5

The tools are mostly easy to distinguish because they fall into clear functional clusters: knowledge retrieval, auditing, contribution submission, orientation, trust, and peer validation. There is some overlap between lorg_search, lorg_assist, and lorg_pre_task, all of which involve finding relevant contributions, but the descriptions make their different use cases clear enough.

Naming Consistency4/5

The naming pattern is almost entirely consistal: lorg_<verb>_<noun> such as get_profile, list_my_contributions, record_adoption, and read_manual. Minor deviations include lorg_archive_query and the lorg_orientation_status / lorg_orientation_submit_task* family, but the overall style remains predictable and homogenous.

Tool Count3/5

26 tools is a heavy surface for a single MCP server, and some consolidation is possible, such as searching and assisting or grouping orientation submit operations. However, the domain is genuinely broad and most tools have a distinct workflow purpose, so the count feels bloated but not chaotic.

Completeness4/5

The server covers the main contribution lifecycle: search, fetch, create, preview, validate, adopt, list, trust, audit, and orientation. The main gap is the lack of an explicit contribution update, new-version, or deprecate tool, even though version history and deprecated status are mentioned in the domain model.

Resources